Brown AI Model Library
Browse Brown’s built-in model catalog. Additional compatible models are available through Ollama and Hugging Face GGUF repositories. Cloud entries require internet; local models depend on hardware and runtime compatibility.
- llava:latest — 7B · Vision
- llama3:latest — 8B · Chat
- mistral:latest — 7B · Chat
- phi3:latest — 3.8B · Reasoning
- gemma2:2b — 2B · Chat
- gemma2:latest — 9B · Chat
- qwen2.5:latest — 7B · Reasoning
- qwen2.5-coder:latest — 7B · Coding
- qwen2.5-coder:1.5b — 1.5B · Coding
- deepseek-r1:latest — 7B · Reasoning
- deepseek-coder-v2:latest — 16B · Coding
- mistral-nemo:latest — 12B · Chat
- phi4:latest — 14B · Reasoning
- moondream:latest — 1.8B · Vision
- bakllava:latest — 7B · Vision
- nomic-embed-text:latest — 137M · Embeddings
- bge-m3:latest — 567M · Embeddings
- snowflake-arctic-embed:latest — 137M · Embeddings
- codellama:latest — 7B · Coding
- tinyllama:latest — 1.1B · Chat
- llama3.2:1b — 1B · Chat
- llama3.2:3b — 3B · Chat
- smollm2:1.7b — 1.7B · Chat
- smollm2:360m — 360M · Chat
- starcoder2:latest — 3B · Coding
- granite3-dense:8b — 8B · Chat
- hermes3:8b — 8B · Reasoning
- vicuna:latest — 7B · Chat
- wizardlm2:latest — 7B · Reasoning
- orca-mini:latest — 3B · Reasoning
- zephyr:latest — 7B · Chat
- command-r:latest — 35B · Reasoning
- Llama-3.2-1B-Instruct (GGUF) — 1B · Chat
- Llama-3.2-3B-Instruct (GGUF) — 3B · Chat
- DeepSeek-R1-Distill-Qwen-1.5B (GGUF) — 1.5B · Reasoning
- DeepSeek-R1-Distill-Qwen-7B (GGUF) — 7B · Reasoning
- Qwen2.5-Coder-1.5B-Instruct (GGUF) — 1.5B · Coding
- Qwen2.5-Coder-7B-Instruct (GGUF) — 7B · Coding
- Mistral-Nemo-Instruct-2407 (GGUF) — 12B · Chat
- Phi-4 (GGUF) — 14B · Reasoning
- SmolLM2-1.7B-Instruct (GGUF) — 1.7B · Chat
- Hermes-3-Llama-3.1-8B (GGUF) — 8B · Reasoning
- Gemma-2-2B-IT (GGUF) — 2B · Chat
- Gemma-2-9B-IT (GGUF) — 9B · Chat
- Phi-3.5-Mini-Instruct (GGUF) — 3.8B · Reasoning
- Mistral-7B-Instruct-v0.2 (GGUF) — 7B · Chat
- Llama-3.1-8B-Instruct (GGUF) — 8B · Chat
- gpt-oss:20b-cloud — 20B · Cloud
- gpt-oss:120b-cloud — 120B · Cloud
- deepseek-v3.1:671b-cloud — 671B · Cloud
- deepseek-r1:70b-cloud — 70B · Cloud
- qwen3-coder:480b-cloud — 480B · Cloud
- qwen2.5:72b-cloud — 72B · Cloud
- llama3.3:70b-cloud — 70B · Cloud
- minimax-m2.7-cloud — CLOUD · Cloud