Free LLM Models Directory
Discover free and open-source large language models for text generation, code completion, and embeddings.
The Ultimate Free LLM Models Directory
Welcome to the most comprehensive directory of free and open-source LLM models. Whether you're a developer, researcher, or AI enthusiast, our curated collection helps you discover powerful language models that you can run locally, fine-tune, or integrate into your applications.
Our directory features models from leading providers including Meta's Llama 2, Mistral AI, Microsoft's Phi, and hundreds more on Hugging Face. All models are verified to have permissive licenses allowing commercial use.
From text generation and code completion to embeddings and multimodal models - find everything you need to build the next generation of AI applications!
Showing 385-432 of 576 models
granite3.1-moe
LLM Models
granite3.1-moe is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
orca-mini
LLM Models
orca-mini is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
starcoder2
LLM Models
starcoder2 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
mixtral
LLM Models
mixtral is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
deepseek-coder-v2
LLM Models
deepseek-coder-v2 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
llama2-uncensored
LLM Models
llama2-uncensored is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
falcon3
LLM Models
falcon3 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
nemotron-3-super
LLM Models
nemotron-3-super is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
glm-5
LLM Models
glm-5 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
llava-llama3
LLM Models
llava-llama3 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
qwq
LLM Models
qwq is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
mistral-small3.2
LLM Models
mistral-small3.2 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
minimax-m2.5
LLM Models
minimax-m2.5 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
gemini-3-flash-preview
LLM Models
gemini-3-flash-preview is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
glm-5.1
LLM Models
glm-5.1 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
minimax-m2.7
LLM Models
minimax-m2.7 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
qwen2.5vl
LLM Models
qwen2.5vl is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
glm-4.6
LLM Models
glm-4.6 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
minimax-m2
LLM Models
minimax-m2 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
glm-4.7
LLM Models
glm-4.7 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
deepseek-v3.2
LLM Models
deepseek-v3.2 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
kimi-k2-thinking
LLM Models
kimi-k2-thinking is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
minimax-m2.1
LLM Models
minimax-m2.1 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
cogito
LLM Models
cogito is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
qwen3.6
LLM Models
qwen3.6 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
qwen3-embedding
LLM Models
qwen3-embedding is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
dolphin-llama3
LLM Models
dolphin-llama3 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
smollm
LLM Models
smollm is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
glm-ocr
LLM Models
glm-ocr is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
dolphin-mixtral
LLM Models
dolphin-mixtral is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
gemma3n
LLM Models
gemma3n is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
llama4
LLM Models
llama4 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
translategemma
LLM Models
translategemma is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
phi4-reasoning
LLM Models
phi4-reasoning is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
dolphin-phi
LLM Models
dolphin-phi is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
dolphin-mistral
LLM Models
dolphin-mistral is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
phi
LLM Models
phi is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
qwen3-coder-next
LLM Models
qwen3-coder-next is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
magistral
LLM Models
magistral is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
command-r
LLM Models
command-r is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
hermes3
LLM Models
hermes3 is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
granite-code
LLM Models
granite-code is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
embeddinggemma
LLM Models
embeddinggemma is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
glm-4.7-flash
LLM Models
glm-4.7-flash is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
moondream
LLM Models
moondream is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
codestral
LLM Models
codestral is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
deepscaler
LLM Models
deepscaler is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
yi
LLM Models
yi is a model entry associated with Ollama. This listing is intended to help developers, researchers, students, and AI application builders discover and organize available language or generative AI models for experimentation, prototyping, model comparison, and software integration. The supplied dataset does not include a model-specific capability description for this record, so capabilities such as reasoning, coding, instruction following, multilingual support, vision or audio processing, tool use, structured outputs, and long-context processing should not be assumed from the model name alone. Before using this model in an application, review the linked provider or model documentation for its architecture or model family, supported modalities, context window, input and output formats, API requirements, licensing terms, pricing or free-tier conditions, rate limits, safety constraints, and current availability. Production deployments should additionally test model quality, latency, reliability, privacy requirements, and workload-specific performance using representative data from the intended application.
Frequently Asked Questions About LLM Models
What are LLM models and how do they work?
Large Language Models (LLMs) are AI models trained on vast amounts of text data to understand and generate human-like text. They use transformer architecture and can perform tasks like text generation, translation, summarization, and code completion.
Which LLM models are free to use?
Many LLM models are freely available including Llama 2, Mistral, Mixtral, Phi-2, and various models on Hugging Face. Our directory features only models with permissive licenses that allow commercial use.
How do I run LLM models locally?
You can run LLMs locally using tools like Ollama, LM Studio, or text-generation-webui. Most models require significant GPU memory (8GB+ VRAM recommended). Smaller models like Phi-2 and Llama 2 7B can run on consumer hardware.
What's the difference between open-source and proprietary LLMs?
Open-source LLMs like Llama 2 and Mistral have publicly available weights and can be run locally or fine-tuned. Proprietary models like GPT-4 are only accessible via API. Open-source models offer more control and privacy.
Can I use these LLM models for commercial projects?
Most models in our directory have permissive licenses (Apache 2.0, MIT) allowing commercial use. Always check the specific model's license on Hugging Face or the provider's website before using in production.