LLM Finder

Match local LLMs to your GPU. Filter by VRAM + use case, then copy the download command.

8 GB12 GB16 GB24 GB48 GB80 GB
allcodingchatresearchcreativemath

16 models fit 16GB for math

Data powered by llmfit ↗

Qwen2.5-Coder-32B-Instruct

32Bq2_K • 13.6GB

Family: Qwen

Estimated speed: 20-30 tok/s

Context: 33k

License: Apache-2.0

codingchatmathresearch
ollama pull qwen2.5-coder:32b

DeepSeek-Coder-33B-Instruct

33Bq2_K • 14GB

Family: DeepSeek

Estimated speed: 20-30 tok/s

Context: 16k

License: DeepSeek License

codingchatmath
ollama pull deepseek-coder:33b

Qwen2.5-32B-Instruct

32Bq2_K • 13.6GB

Family: Qwen

Estimated speed: 21-31 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmathcreative
ollama pull qwen2.5:32b

Gemma-2-27B-Instruct

27Bq3_K_M • 15GB

Family: Gemma

Estimated speed: 18-28 tok/s

Context: 8k

License: Gemma Terms

chatcodingresearchcreativemath
ollama pull gemma2:27b

Yi-1.5-34B-Chat

34Bq2_K • 14.4GB

Family: Yi

Estimated speed: 20-30 tok/s

Context: 33k

License: Apache-2.0

chatresearchcreativemath
ollama pull yi:34b

DeepSeek-R1-Distill-Qwen-14B

14Bq5_K_M • 12.9GB

Family: DeepSeek

Estimated speed: 24-34 tok/s

Context: 33k

License: MIT

mathresearchcoding
ollama pull deepseek-r1:14b

CodeLlama-34B-Instruct

34Bq2_K • 14.4GB

Family: CodeLlama

Estimated speed: 21-31 tok/s

Context: 16k

License: Llama 2 Community

codingmath
ollama pull codellama:34b

Phi-4-14B-Instruct

14Bq5_K_M • 12.9GB

Family: Phi

Estimated speed: 25-35 tok/s

Context: 128k

License: MIT

codingmathresearchchat
ollama pull phi4:14b

Qwen2.5-Coder-14B-Instruct

14Bq5_K_M • 12.9GB

Family: Qwen

Estimated speed: 25-35 tok/s

Context: 33k

License: Apache-2.0

codingchatmath
ollama pull qwen2.5-coder:14b

Phi-3-medium-128k-instruct

14Bq5_K_M • 12.9GB

Family: Phi

Estimated speed: 25-35 tok/s

Context: 131k

License: MIT

codingchatresearchmath
ollama pull phi3:medium

StarCoder2-15B-Instruct

15Bq5_K_M • 13.7GB

Family: StarCoder

Estimated speed: 24-34 tok/s

Context: 16k

License: OpenRAIL-M

codingmath
ollama pull starcoder2:15b

DeepSeek-R1-Distill-Llama-8B

8Bq8_0 • 11.2GB

Family: DeepSeek

Estimated speed: 30-40 tok/s

Context: 33k

License: MIT

mathresearchchat
ollama pull deepseek-r1:8b

Qwen2.5-14B-Instruct

14Bq5_K_M • 12.9GB

Family: Qwen

Estimated speed: 26-36 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmath
ollama pull qwen2.5:14b

DeepSeek-R1-Distill-Qwen-7B

7Bq8_0 • 10.1GB

Family: DeepSeek

Estimated speed: 33-43 tok/s

Context: 33k

License: MIT

mathresearchcoding
ollama pull deepseek-r1:7b

CodeLlama-13B-Instruct

13Bq5_K_M • 12.1GB

Family: CodeLlama

Estimated speed: 30-40 tok/s

Context: 16k

License: Llama 2 Community

codingmath
ollama pull codellama:13b

Qwen2.5-7B-Instruct

7Bq8_0 • 10.1GB

Family: Qwen

Estimated speed: 37-47 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmath
ollama pull qwen2.5:7b