LLM Finder
Match local LLMs to your GPU. Filter by VRAM + use case, then copy the download command.
12 models fit 8GB for creative
Data powered by llmfit ↗Mistral-Nemo-12B-Instruct
12Bq3_K_M • 7.2GBFamily: Mistral
Estimated speed: 21-31 tok/s
Context: 128k
License: Apache-2.0
ollama pull mistral-nemo:12bCommand-R-7B
7Bq5_K_M • 7.1GBFamily: Cohere
Estimated speed: 24-34 tok/s
Context: 128k
License: CC-BY-NC
ollama pull command-r:7bDolphin-2.9.2-Qwen2-7B
7Bq5_K_M • 7.1GBFamily: Dolphin
Estimated speed: 24-34 tok/s
Context: 33k
License: Apache-2.0
ollama pull dolphin3:8bYi-1.5-9B-Chat
9Bq4_K_M • 7.1GBFamily: Yi
Estimated speed: 25-35 tok/s
Context: 33k
License: Apache-2.0
ollama pull yi:9bLlama-3-8B-Instruct
8Bq5_K_M • 8GBFamily: Llama
Estimated speed: 25-35 tok/s
Context: 8k
License: Llama 3 Community
ollama pull llama3:8bOpenHermes-2.5-Mistral-7B
7Bq5_K_M • 7.1GBFamily: Nous
Estimated speed: 26-36 tok/s
Context: 33k
License: Apache-2.0
ollama pull openhermesLlama-3.1-8B-Instruct
8Bq5_K_M • 8GBFamily: Llama
Estimated speed: 26-36 tok/s
Context: 131k
License: Llama 3.1 Community
ollama pull llama3.1:8bGemma-2-9B-Instruct
9Bq4_K_M • 7.1GBFamily: Gemma
Estimated speed: 26-36 tok/s
Context: 8k
License: Gemma Terms
ollama pull gemma2:9bZephyr-7B-beta
7Bq5_K_M • 7.1GBFamily: Zephyr
Estimated speed: 26-36 tok/s
Context: 33k
License: MIT
ollama pull zephyr:7bOpenChat-3.6-8B
8Bq5_K_M • 8GBFamily: OpenChat
Estimated speed: 28-38 tok/s
Context: 8k
License: Apache-2.0
ollama pull openchat:8bLlama-3.2-3B-Instruct
3Bq8_0 • 5.3GBFamily: Llama
Estimated speed: 36-46 tok/s
Context: 131k
License: Llama 3.2 Community
ollama pull llama3.2:3bGemma-2-2B-Instruct
2Bfp16 • 6.9GBFamily: Gemma
Estimated speed: 37-47 tok/s
Context: 8k
License: Gemma Terms
ollama pull gemma2:2b