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

21 models fit 8GB for coding

Data powered by llmfit ↗

Phi-4-14B-Instruct

14Bq2_K • 6.4GB

Family: Phi

Estimated speed: 21-31 tok/s

Context: 128k

License: MIT

codingmathresearchchat
ollama pull phi4:14b

Phi-3-medium-128k-instruct

14Bq2_K • 6.4GB

Family: Phi

Estimated speed: 22-32 tok/s

Context: 131k

License: MIT

codingchatresearchmath
ollama pull phi3:medium

Mistral-Nemo-12B-Instruct

12Bq3_K_M • 7.2GB

Family: Mistral

Estimated speed: 21-31 tok/s

Context: 128k

License: Apache-2.0

chatcodingcreative
ollama pull mistral-nemo:12b

Qwen2.5-Coder-14B-Instruct

14Bq2_K • 6.4GB

Family: Qwen

Estimated speed: 23-33 tok/s

Context: 33k

License: Apache-2.0

codingchatmath
ollama pull qwen2.5-coder:14b

Qwen2.5-14B-Instruct

14Bq2_K • 6.4GB

Family: Qwen

Estimated speed: 23-33 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmath
ollama pull qwen2.5:14b

DeepSeek-R1-Distill-Qwen-14B

14Bq2_K • 6.4GB

Family: DeepSeek

Estimated speed: 25-35 tok/s

Context: 33k

License: MIT

mathresearchcoding
ollama pull deepseek-r1:14b

Qwen2.5-Coder-7B-Instruct

7Bq5_K_M • 7.1GB

Family: Qwen

Estimated speed: 24-34 tok/s

Context: 33k

License: Apache-2.0

codingchat
ollama pull qwen2.5-coder:7b

Dolphin-2.9.2-Qwen2-7B

7Bq5_K_M • 7.1GB

Family: Dolphin

Estimated speed: 24-34 tok/s

Context: 33k

License: Apache-2.0

chatcreativecoding
ollama pull dolphin3:8b

Qwen2.5-7B-Instruct

7Bq5_K_M • 7.1GB

Family: Qwen

Estimated speed: 25-35 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmath
ollama pull qwen2.5:7b

CodeLlama-7B-Instruct

7Bq5_K_M • 7.1GB

Family: CodeLlama

Estimated speed: 26-36 tok/s

Context: 16k

License: Llama 2 Community

coding
ollama pull codellama:7b

Phi-4-mini-instruct

3.8Bq8_0 • 6.3GB

Family: Phi

Estimated speed: 28-38 tok/s

Context: 128k

License: MIT

chatcodingresearch
ollama pull phi4-mini

DeepSeek-R1-Distill-Qwen-7B

7Bq5_K_M • 7.1GB

Family: DeepSeek

Estimated speed: 28-38 tok/s

Context: 33k

License: MIT

mathresearchcoding
ollama pull deepseek-r1:7b

Phi-3-mini-4k-instruct

3.8Bq8_0 • 6.3GB

Family: Phi

Estimated speed: 30-40 tok/s

Context: 4k

License: MIT

chatcoding
ollama pull phi3:mini

DeepSeek-Coder-6.7B-Instruct

6.7Bq5_K_M • 6.9GB

Family: DeepSeek

Estimated speed: 30-40 tok/s

Context: 16k

License: DeepSeek License

codingchat
ollama pull deepseek-coder:6.7b

StarCoder2-15B-Instruct

15Bq2_K • 6.8GB

Family: StarCoder

Estimated speed: 31-41 tok/s

Context: 16k

License: OpenRAIL-M

codingmath
ollama pull starcoder2:15b

WizardLM-2-7B

7Bq5_K_M • 7.1GB

Family: WizardLM

Estimated speed: 30-40 tok/s

Context: 33k

License: Llama 2 Community

chatcoding
ollama pull wizardlm2:7b

Qwen2.5-3B-Instruct

3Bq8_0 • 5.3GB

Family: Qwen

Estimated speed: 35-45 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearch
ollama pull qwen2.5:3b

CodeGemma-7B-Instruct

7Bq5_K_M • 7.1GB

Family: Gemma

Estimated speed: 31-41 tok/s

Context: 8k

License: Gemma Terms

codingchat
ollama pull codegemma:7b

CodeLlama-13B-Instruct

13Bq3_K_M • 7.8GB

Family: CodeLlama

Estimated speed: 32-42 tok/s

Context: 16k

License: Llama 2 Community

codingmath
ollama pull codellama:13b

StarCoder2-7B-Instruct

7Bq5_K_M • 7.1GB

Family: StarCoder

Estimated speed: 34-44 tok/s

Context: 16k

License: OpenRAIL-M

coding
ollama pull starcoder2:7b

StarCoder2-3B-Instruct

3Bq8_0 • 5.3GB

Family: StarCoder

Estimated speed: 42-52 tok/s

Context: 16k

License: OpenRAIL-M

coding
ollama pull starcoder2:3b