Browse by model
Pick a model to see the VRAM it needs and which GPUs can run it. Minimum VRAM is for the smallest quantization with 16K context.
- Beam 1.0 501B A23B 293.5 GB+
- Codestral 22B 16.7 GB+
- DeepSeek Coder 6.7B 11.9 GB+
- DeepSeek R1 0528 410.3 GB+
- DeepSeek R1 Distill Llama 70B 47.4 GB+
- DeepSeek R1 Distill Qwen 7B 5.5 GB+
- DeepSeek R1 Distill Qwen 14B 11.9 GB+
- DeepSeek R1 Distill Qwen 32B 23.8 GB+
- DeepSeek V4 Flash 162.3 GB+
- DeepSeek V4 Pro 901.0 GB+
- Devstral Small 24B 16.8 GB+
- Flint 40B A2.5B 24.0 GB+
- Gemma 2 9B 8.3 GB+
- Gemma 2 27B 19.5 GB+
- Gemma 3 4B 2.8 GB+
- Gemma 3 12B 8.3 GB+
- Gemma 3 27B 17.8 GB+
- Gemma 4 12B 6.9 GB+
- Gemma 4 26B A4B 16.2 GB+
- Gemma 4 31B 19.5 GB+
- Gemma 4 E2B 3.3 GB+
- Gemma 4 E4B 5.3 GB+
- GLM 5 425.9 GB+
- GLM 5.1 461.0 GB+
- GLM 5.3 747.7 GB+
- GLM 5.3 Flash 176.2 GB+
- GLM-4.6 217.1 GB+
- GLM-4.7 Flash 19.1 GB+
- GPT-OSS 20B 12.0 GB+
- K2-Horizon 7B 7.4 GB+
- Laguna XS 2.1 19.7 GB+
- LFM2.5 2.6B 1.8 GB+
- LFM2.5 24B A2B 13.8 GB+
- Llama 3.1 8B 6.9 GB+
- Llama 3.2 1B 1.3 GB+
- Llama 3.2 3B 3.7 GB+
- Llama 3.2 Vision 11B 7.9 GB+
- Llama 3.3 70B 47.4 GB+
- Llama 4 Maverick 245.9 GB+
- Llama 4 Scout 68.3 GB+
- Magistral Small 24B 16.8 GB+
- MiMo V2.5 191.0 GB+
- MiMo V2.5 Pro 631.6 GB+
- MiMo V2.6 Distill Qwen 9B 5.9 GB+
- MiniCPM-V 4.7 35B A3B 20.0 GB+
- MiniMax M2.1 139.2 GB+
- MiniMax M2.5 132.6 GB+
- Ministral 8B 7.3 GB+
- Mistral Large 3 675B 380.1 GB+
- Mistral Nemo 12B 10.7 GB+
- Mistral Small 3.1 24B 16.8 GB+
- Mistral Small 4 81.4 GB+
- Muse Glimmer 30B 15.8 GB+
- Muse Spark Open 816B A42B 466.3 GB+
- Nemotron 3 Nano 4B 3.0 GB+
- Nemotron 3.5 Bolt 74B A9B 73.6 GB+
- Nemotron 3.5 Bolt E4B 6.0 GB+
- Nemotron 3.5 Lightning 30B A3B 23.8 GB+
- Nemotron 3.5 Super VL 120B A12B 65.4 GB+
- Nemotron Cascade 2 30B A3B 23.1 GB+
- Nemotron Nano 12B 7.7 GB+
- Ornith 1.5 9B 5.9 GB+
- Ornith 1.5 35B A3B 20.5 GB+
- Ornith 1.5 122B 71.0 GB+
- Ornith 1.5 397B 228.0 GB+
- Phi-3 Mini 3.8B 8.2 GB+
- Phi-4 14B 12.1 GB+
- Phi-4 Mini 3.8B 4.4 GB+
- Qwen 2.5 3B 2.5 GB+
- Qwen 2.5 7B 5.5 GB+
- Qwen 2.5 14B 11.9 GB+
- Qwen 2.5 32B 23.8 GB+
- Qwen 2.5 72B 52.3 GB+
- Qwen 2.5 Coder 7B 5.5 GB+
- Qwen 2.5 Coder 14B 11.9 GB+
- Qwen 2.5 Coder 32B 23.8 GB+
- Qwen 2.5 VL 3B 2.5 GB+
- Qwen 2.5 VL 7B 5.5 GB+
- Qwen 2.5 VL 72B 52.3 GB+
- Qwen3 8B 7.2 GB+
- Qwen3 32B 23.7 GB+
- Qwen3 Coder 30B-A3B 20.1 GB+
- Qwen3 Next 80B-A3B 48.8 GB+
- Qwen3.5 0.8B 0.7 GB+
- Qwen3.5 2B 1.4 GB+
- Qwen3.5 4B 3.0 GB+
- Qwen3.5 9B 5.8 GB+
- Qwen3.5 27B 16.6 GB+
- Qwen3.5 35B A3B 20.8 GB+
- Qwen3.5 122B A10B 71.6 GB+
- Qwen3.5 397B A17B 227.8 GB+
- Qwen3.6 27B 17.5 GB+
- Qwen3.6 35B A3B 22.6 GB+
- Qwen3.8 27B 16.3 GB+
- Qwen3.8 Flash Next 111.8 GB+
- QwQ 32B 23.8 GB+
- SmallThinker 3B 2.5 GB+
- StarCoder2 15B 11.1 GB+
- Step 3.5 Flash 121.8 GB+
- Step 3.7 Flash 106.6 GB+