Skip to content

AI Models

69 open-weight models with VRAM requirements and hardware compatibility data.

DeepSeek R1 14B

14B

DeepSeek

Min 9.9 GB
text-generation code-generation reasoning popular

DeepSeek R1 32B

32B

DeepSeek

Min 20.7 GB
text-generation code-generation reasoning popular

DeepSeek R1 8B

8B

DeepSeek

Min 7.5 GB
text-generation code-generation reasoning popular

DeepSeek V3

671B

DeepSeek

Min 362 GB
text-generation code-generation reasoning popular

Devstral 24B

24B

Mistral AI

Min 17 GB
text-generation code-generation reasoning popular

Gemma 2 9B

9B

Google

Min 6.9 GB
text-generation code-generation reasoning popular

Gemma 3 12B

12B

Google

Min 10.5 GB
text-generation code-generation reasoning popular

Gemma 3 27B

27B

Google

Min 20 GB
text-generation code-generation reasoning popular

Gemma 3 4B

4B

Google

Min 5 GB
text-generation code-generation reasoning popular

Llama 3.1 8B

8B

Meta

Min 6.3 GB
text-generation code-generation multilingual popular

Llama 3.2 Vision 11B

11B

Meta

Min 8.5 GB
text-generation vision reasoning popular

Llama 3.3 70B

70B

Meta

Min 43.5 GB
text-generation code-generation reasoning popular

Llama 4 Scout (109B/17B active)

109B

Meta

Min 72 GB
text-generation code-generation reasoning popular

Mistral 7B

7B

Mistral AI

Min 5.7 GB
text-generation code-generation multilingual popular

Mistral Nemo 12B

12B

Mistral AI

Min 9.5 GB
text-generation code-generation reasoning popular

Mistral Small 3.1 24B

24B

Mistral AI

Min 18 GB
text-generation code-generation reasoning popular

Mixtral 8x7B

47B

Mistral AI

Min 29.7 GB
text-generation code-generation reasoning popular

Phi-4 14B

14B

Microsoft

Min 9.9 GB
text-generation code-generation reasoning popular

Phi-4 Mini 3.8B

3.8B

Microsoft

Min 4.5 GB
text-generation code-generation reasoning popular

Qwen 2.5 32B

32B

Alibaba

Min 20.7 GB
text-generation code-generation reasoning popular

Qwen 2.5 Coder 32B

32B

Alibaba

Min 23 GB
text-generation code-generation reasoning popular

Qwen 2.5 Coder 7B

7B

Alibaba

Min 5.7 GB
text-generation code-generation popular

Qwen 3 14B

14B

Alibaba

Min 12 GB
text-generation code-generation reasoning popular

Qwen 3 30B-A3B (MoE)

30B

Alibaba

Min 22 GB
text-generation code-generation reasoning popular

Qwen 3 32B

32B

Alibaba

Min 23 GB
text-generation code-generation reasoning popular

Qwen 3 4B

4B

Alibaba

Min 4.5 GB
text-generation code-generation reasoning popular

Qwen 3 8B

8B

Alibaba

Min 7.5 GB
text-generation code-generation reasoning popular

QwQ 32B

32B

Alibaba

Min 21.5 GB
text-generation code-generation reasoning popular

Codestral 22B

22B

Mistral AI

Min 14.7 GB
text-generation code-generation

Cogito 32B

32B

Deep Cogito

Min 21.5 GB
text-generation code-generation reasoning

Cogito 70B

70B

Deep Cogito

Min 43 GB
text-generation code-generation reasoning

Cogito 8B

8B

Deep Cogito

Min 7.5 GB
text-generation code-generation reasoning

Command A 111B

111B

Cohere

Min 61 GB
text-generation code-generation reasoning

Command R 35B

35B

Cohere

Min 22.5 GB
text-generation reasoning multilingual

Command R+ 104B

104B

Cohere

Min 57 GB
text-generation code-generation reasoning

DeepSeek R1 1.5B

1.5B

DeepSeek

Min 2 GB
text-generation reasoning math

DeepSeek R1 671B

671B

DeepSeek

Min 362 GB
text-generation code-generation reasoning

DeepSeek R1 70B

70B

DeepSeek

Min 43.5 GB
text-generation code-generation reasoning

DeepSeek R1 7B

7B

DeepSeek

Min 5.7 GB
text-generation code-generation reasoning

DeepSeek V3-0324

671B

DeepSeek

Min 362 GB
text-generation code-generation reasoning

Devstral 2 123B

123B

Mistral AI

Min 67 GB
text-generation code-generation reasoning

Falcon 3 10B

10B

TII

Min 8.5 GB
text-generation code-generation reasoning

Falcon 3 7B

7B

TII

Min 6.8 GB
text-generation code-generation reasoning

Gemma 2 27B

27B

Google

Min 17.7 GB
text-generation code-generation reasoning

Gemma 2 2B

2B

Google

Min 2.7 GB
text-generation code-generation multilingual

Gemma 3 1B

1B

Google

Min 1.5 GB
text-generation multilingual summarization

Gemma 3n E2B

2B

Google

Min 3.3 GB
text-generation reasoning multilingual

Gemma 3n E4B

4B

Google

Min 4.5 GB
text-generation reasoning multilingual

Llama 3.1 405B

405B

Meta

Min 244.5 GB
text-generation code-generation reasoning

Llama 3.1 70B

70B

Meta

Min 43.5 GB
text-generation code-generation reasoning

Llama 3.2 1B

1B

Meta

Min 2.1 GB
text-generation summarization

Llama 3.2 3B

3B

Meta

Min 3.3 GB
text-generation code-generation multilingual

Llama 3.2 Vision 90B

90B

Meta

Min 50 GB
text-generation vision reasoning

Llama 4 Maverick

400B

Meta

Min 228 GB
text-generation code-generation reasoning

Magistral Small 24B

24B

Mistral AI

Min 17 GB
text-generation code-generation reasoning

Mistral Large 2 123B

123B

Mistral AI

Min 67 GB
text-generation code-generation reasoning

Mixtral 8x22B

141B

Mistral AI

Min 86 GB
text-generation code-generation reasoning

Nemotron 3 Nano 8B

8B

NVIDIA

Min 7.5 GB
text-generation code-generation reasoning

Phi-3 Mini 3.8B

3.8B

Microsoft

Min 3.8 GB
text-generation code-generation reasoning

Phi-4 Reasoning 14B

14B

Microsoft

Min 11 GB
text-generation code-generation reasoning

Qwen 2.5 14B

14B

Alibaba

Min 9.9 GB
text-generation code-generation reasoning

Qwen 2.5 72B

72B

Alibaba

Min 44.7 GB
text-generation code-generation reasoning

Qwen 2.5 7B

7B

Alibaba

Min 5.7 GB
text-generation code-generation multilingual

Qwen 2.5 Coder 14B

14B

Alibaba

Min 12 GB
text-generation code-generation

Qwen 2.5 VL 72B

72B

Alibaba

Min 41 GB
text-generation vision reasoning

Qwen 2.5 VL 7B

7B

Alibaba

Min 7 GB
text-generation vision reasoning

Qwen 3 0.6B

600M

Alibaba

Min 2.5 GB
text-generation reasoning multilingual

Qwen 3 235B-A22B

235B

Alibaba

Min 138 GB
text-generation code-generation reasoning

StarCoder2 15B

15B

BigCode

Min 10.5 GB
text-generation code-generation