LLM Finder
Match local LLMs to your GPU. Filter by VRAM + use case, then copy the download command.
11 models fit 12GB for math
Data powered by llmfit ↗Phi-4-14B-Instruct
14Bq4_K_M • 10.4GBFamily: Phi
Estimated speed: 21-31 tok/s
Context: 128k
License: MIT
ollama pull phi4:14bPhi-3-medium-128k-instruct
14Bq4_K_M • 10.4GBFamily: Phi
Estimated speed: 22-32 tok/s
Context: 131k
License: MIT
ollama pull phi3:mediumQwen2.5-Coder-14B-Instruct
14Bq4_K_M • 10.4GBFamily: Qwen
Estimated speed: 23-33 tok/s
Context: 33k
License: Apache-2.0
ollama pull qwen2.5-coder:14bDeepSeek-R1-Distill-Llama-8B
8Bq8_0 • 11.2GBFamily: DeepSeek
Estimated speed: 21-31 tok/s
Context: 33k
License: MIT
ollama pull deepseek-r1:8bQwen2.5-14B-Instruct
14Bq4_K_M • 10.4GBFamily: Qwen
Estimated speed: 23-33 tok/s
Context: 33k
License: Apache-2.0
ollama pull qwen2.5:14bGemma-2-27B-Instruct
27Bq2_K • 11.6GBFamily: Gemma
Estimated speed: 22-32 tok/s
Context: 8k
License: Gemma Terms
ollama pull gemma2:27bDeepSeek-R1-Distill-Qwen-14B
14Bq4_K_M • 10.4GBFamily: DeepSeek
Estimated speed: 25-35 tok/s
Context: 33k
License: MIT
ollama pull deepseek-r1:14bQwen2.5-7B-Instruct
7Bq8_0 • 10.1GBFamily: Qwen
Estimated speed: 27-37 tok/s
Context: 33k
License: Apache-2.0
ollama pull qwen2.5:7bDeepSeek-R1-Distill-Qwen-7B
7Bq8_0 • 10.1GBFamily: DeepSeek
Estimated speed: 30-40 tok/s
Context: 33k
License: MIT
ollama pull deepseek-r1:7bStarCoder2-15B-Instruct
15Bq4_K_M • 11.1GBFamily: StarCoder
Estimated speed: 30-40 tok/s
Context: 16k
License: OpenRAIL-M
ollama pull starcoder2:15bCodeLlama-13B-Instruct
13Bq4_K_M • 9.8GBFamily: CodeLlama
Estimated speed: 35-45 tok/s
Context: 16k
License: Llama 2 Community
ollama pull codellama:13b