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

35 models fit 48GB for coding

Data powered by llmfit ↗

Qwen2.5-72B-Instruct

72Bq3_K_M • 38.4GB

Family: Qwen

Estimated speed: 37-47 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmathcreative

ollama pull qwen2.5:72b

Llama-3.3-70B-Instruct

70Bq4_K_M • 47.4GB

Family: Llama

Estimated speed: 17-27 tok/s

Context: 131k

License: Llama 3.3 Community

chatcodingresearchcreativemath

ollama pull llama3.3:70b

Qwen2.5-Coder-32B-Instruct

32Bq8_0 • 39.6GB

Family: Qwen

Estimated speed: 35-45 tok/s

Context: 33k

License: Apache-2.0

codingchatmathresearch

ollama pull qwen2.5-coder:32b

Nous-Hermes-2-Mixtral-8x7B-DPO

46.7B MoEq5_K_M • 39.9GB

Family: Nous

Estimated speed: 35-45 tok/s

Context: 33k

License: Apache-2.0

chatcreativecoding

ollama pull nous-hermes2-mixtral

DeepSeek-R1-Distill-Llama-70B

70Bq4_K_M • 47.4GB

Family: DeepSeek

Estimated speed: 18-28 tok/s

Context: 33k

License: MIT

mathresearchcodingchat

ollama pull deepseek-r1:70b

Qwen2.5-32B-Instruct

32Bq8_0 • 39.6GB

Family: Qwen

Estimated speed: 37-47 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmathcreative

ollama pull qwen2.5:32b

Phi-4-14B-Instruct

14Bfp16 • 33.3GB

Family: Phi

Estimated speed: 52-62 tok/s

Context: 128k

License: MIT

codingmathresearchchat

ollama pull phi4:14b

Phi-3-medium-128k-instruct

14Bfp16 • 33.3GB

Family: Phi

Estimated speed: 53-63 tok/s

Context: 131k

License: MIT

codingchatresearchmath

ollama pull phi3:medium

Mistral-Nemo-12B-Instruct

12Bfp16 • 28.9GB

Family: Mistral

Estimated speed: 64-74 tok/s

Context: 128k

License: Apache-2.0

chatcodingcreative

ollama pull mistral-nemo:12b

Qwen2.5-Coder-14B-Instruct

14Bfp16 • 33.3GB

Family: Qwen

Estimated speed: 54-64 tok/s

Context: 33k

License: Apache-2.0

codingchatmath

ollama pull qwen2.5-coder:14b

Qwen2.5-14B-Instruct

14Bfp16 • 33.3GB

Family: Qwen

Estimated speed: 54-64 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmath

ollama pull qwen2.5:14b

Mixtral-8x22B-Instruct

141B MoEq3_K_M • 47.8GB

Family: Mistral

Estimated speed: 22-32 tok/s

Context: 66k

License: Apache-2.0

chatcodingresearchcreativemath

ollama pull mixtral:8x22b

WizardLM-2-8x22B

141B MoEq3_K_M • 47.8GB

Family: WizardLM

Estimated speed: 22-32 tok/s

Context: 66k

License: Llama 2 Community

chatcodingresearchcreative

ollama pull wizardlm2:8x22b

Gemma-2-27B-Instruct

27Bq8_0 • 33.7GB

Family: Gemma

Estimated speed: 54-64 tok/s

Context: 8k

License: Gemma Terms

chatcodingresearchcreativemath

ollama pull gemma2:27b

DeepSeek-R1-Distill-Qwen-14B

14Bfp16 • 33.3GB

Family: DeepSeek

Estimated speed: 56-66 tok/s

Context: 33k

License: MIT

mathresearchcoding

ollama pull deepseek-r1:14b

DBRX-Instruct

132B MoEq3_K_M • 44.7GB

Family: Databricks

Estimated speed: 29-39 tok/s

Context: 33k

License: Databricks Open

chatcodingresearch

ollama pull dbrx

Mixtral-8x7B-Instruct

46.7B MoEq5_K_M • 39.9GB

Family: Mistral

Estimated speed: 41-51 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchcreative

ollama pull mixtral:8x7b

Qwen2.5-Coder-7B-Instruct

7Bfp16 • 17.9GB

Family: Qwen

Estimated speed: 94-104 tok/s

Context: 33k

License: Apache-2.0

codingchat

ollama pull qwen2.5-coder:7b

Dolphin-2.9.2-Qwen2-7B

7Bfp16 • 17.9GB

Family: Dolphin

Estimated speed: 94-104 tok/s

Context: 33k

License: Apache-2.0

chatcreativecoding

ollama pull dolphin3:8b

DeepSeek-Coder-33B-Instruct

33Bq8_0 • 40.7GB

Family: DeepSeek

Estimated speed: 40-50 tok/s

Context: 16k

License: DeepSeek License

codingchatmath

ollama pull deepseek-coder:33b

Qwen2.5-7B-Instruct

7Bfp16 • 17.9GB

Family: Qwen

Estimated speed: 95-105 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearchmath

ollama pull qwen2.5:7b

CodeLlama-7B-Instruct

7Bfp16 • 17.9GB

Family: CodeLlama

Estimated speed: 96-106 tok/s

Context: 16k

License: Llama 2 Community

coding

ollama pull codellama:7b

Phi-4-mini-instruct

3.8Bfp16 • 10.9GB

Family: Phi

Estimated speed: 113-123 tok/s

Context: 128k

License: MIT

chatcodingresearch

ollama pull phi4-mini

Command-R-35B

35Bq8_0 • 43.1GB

Family: Cohere

Estimated speed: 37-47 tok/s

Context: 128k

License: CC-BY-NC

researchchatcoding

ollama pull command-r:35b

CodeLlama-34B-Instruct

34Bq8_0 • 41.9GB

Family: CodeLlama

Estimated speed: 40-50 tok/s

Context: 16k

License: Llama 2 Community

codingmath

ollama pull codellama:34b

DeepSeek-R1-Distill-Qwen-7B

7Bfp16 • 17.9GB

Family: DeepSeek

Estimated speed: 98-108 tok/s

Context: 33k

License: MIT

mathresearchcoding

ollama pull deepseek-r1:7b

Phi-3-mini-4k-instruct

3.8Bfp16 • 10.9GB

Family: Phi

Estimated speed: 115-125 tok/s

Context: 4k

License: MIT

chatcoding

ollama pull phi3:mini

DeepSeek-Coder-6.7B-Instruct

6.7Bfp16 • 17.2GB

Family: DeepSeek

Estimated speed: 101-111 tok/s

Context: 16k

License: DeepSeek License

codingchat

ollama pull deepseek-coder:6.7b

WizardLM-2-7B

7Bfp16 • 17.9GB

Family: WizardLM

Estimated speed: 100-110 tok/s

Context: 33k

License: Llama 2 Community

chatcoding

ollama pull wizardlm2:7b

StarCoder2-15B-Instruct

15Bfp16 • 35.5GB

Family: StarCoder

Estimated speed: 58-68 tok/s

Context: 16k

License: OpenRAIL-M

codingmath

ollama pull starcoder2:15b

Qwen2.5-3B-Instruct

3Bfp16 • 9.1GB

Family: Qwen

Estimated speed: 122-132 tok/s

Context: 33k

License: Apache-2.0

chatcodingresearch

ollama pull qwen2.5:3b

CodeGemma-7B-Instruct

7Bfp16 • 17.9GB

Family: Gemma

Estimated speed: 101-111 tok/s

Context: 8k

License: Gemma Terms

codingchat

ollama pull codegemma:7b

CodeLlama-13B-Instruct

13Bfp16 • 31.1GB

Family: CodeLlama

Estimated speed: 71-81 tok/s

Context: 16k

License: Llama 2 Community

codingmath

ollama pull codellama:13b

StarCoder2-7B-Instruct

7Bfp16 • 17.9GB

Family: StarCoder

Estimated speed: 104-114 tok/s

Context: 16k

License: OpenRAIL-M

coding

ollama pull starcoder2:7b

StarCoder2-3B-Instruct

3Bfp16 • 9.1GB

Family: StarCoder

Estimated speed: 129-139 tok/s

Context: 16k

License: OpenRAIL-M

coding

ollama pull starcoder2:3b