Can I Run It?
作者： Jakub Rusinowski · 最后更新： 2026年6月15日
Pick a model family below to see exactly which GPUs it fits on, with quantization and estimated tokens/sec for each.
Llama 3.3
Llama 3.1 Family
Llama 3.2 Family
Llama 4
Qwen 2.5 Family
Qwen 3
Qwen3-Coder
Qwen 3.5
Qwen 3.6
DeepSeek R1
DeepSeek V3
DeepSeek V3.2
DeepSeek V4
Mistral Family
Mistral Small 3.1
Mistral Small 4
Codestral
Devstral-2
Gemma 2 Family
Gemma 3
Gemma 4
Phi-4 Family
Command R Family
Granite 3.0
IBM Granite 4.1
GLM-4.7 / GLM-Z1
GLM-5
MiniMax M2.5
GPT-oss 120B
Best LLMs by VRAM Tier → | Check Your Hardware