LLM Finder

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

GPU VRAM

8 GB 12 GB 16 GB 24 GB 48 GB 80 GB

Use Case

all coding chat research creative math

28 models fit 8GB for chat

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

DeepSeek-R1-Distill-Llama-8B

8Bq5_K_M • 8GB

Family: DeepSeek

Estimated speed: 21-31 tok/s

Context: 33k

License: MIT

mathresearchchat

ollama pull deepseek-r1:8b

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

Ministral-8B-Instruct

8Bq5_K_M • 8GB

Family: Mistral

Estimated speed: 24-34 tok/s

Context: 128k

License: Mistral Research

chatresearch

ollama pull ministral:8b

Command-R-7B

7Bq5_K_M • 7.1GB

Family: Cohere

Estimated speed: 24-34 tok/s

Context: 128k

License: CC-BY-NC

researchchatcreative

ollama pull command-r:7b

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

Mistral-7B-Instruct-v0.3

7Bq5_K_M • 7.1GB

Family: Mistral

Estimated speed: 24-34 tok/s

Context: 33k

License: Apache-2.0

chatresearch

ollama pull mistral: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

Yi-1.5-9B-Chat

9Bq4_K_M • 7.1GB

Family: Yi

Estimated speed: 25-35 tok/s

Context: 33k

License: Apache-2.0

chatresearchcreative

ollama pull yi:9b

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

Llama-3-8B-Instruct

8Bq5_K_M • 8GB

Family: Llama

Estimated speed: 25-35 tok/s

Context: 8k

License: Llama 3 Community

chatcreative

ollama pull llama3:8b

OpenHermes-2.5-Mistral-7B

7Bq5_K_M • 7.1GB

Family: Nous

Estimated speed: 26-36 tok/s

Context: 33k

License: Apache-2.0

chatcreative

ollama pull openhermes

Llama-3.1-8B-Instruct

8Bq5_K_M • 8GB

Family: Llama

Estimated speed: 26-36 tok/s

Context: 131k

License: Llama 3.1 Community

chatresearchcreative

ollama pull llama3.1:8b

Gemma-2-9B-Instruct

9Bq4_K_M • 7.1GB

Family: Gemma

Estimated speed: 26-36 tok/s

Context: 8k

License: Gemma Terms

chatresearchcreative

ollama pull gemma2:9b

Zephyr-7B-beta

7Bq5_K_M • 7.1GB

Family: Zephyr

Estimated speed: 26-36 tok/s

Context: 33k

License: MIT

chatcreative

ollama pull zephyr:7b

Neural-Chat-7B-v3.3

7Bq5_K_M • 7.1GB

Family: Intel

Estimated speed: 26-36 tok/s

Context: 33k

License: Apache-2.0

chatresearch

ollama pull neural-chat

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

OpenChat-3.6-8B

8Bq5_K_M • 8GB

Family: OpenChat

Estimated speed: 28-38 tok/s

Context: 8k

License: Apache-2.0

chatcreative

ollama pull openchat:8b

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

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

Llama-3.2-3B-Instruct

3Bq8_0 • 5.3GB

Family: Llama

Estimated speed: 36-46 tok/s

Context: 131k

License: Llama 3.2 Community

chatcreative

ollama pull llama3.2:3b

Gemma-2-2B-Instruct

2Bfp16 • 6.9GB

Family: Gemma

Estimated speed: 37-47 tok/s

Context: 8k

License: Gemma Terms

chatcreative

ollama pull gemma2:2b