Can my GPU or Mac run this AI model?

Pick your hardware and a model to see if it fits in memory, the best quantization, and estimated tokens/sec.

Or search:

Popular checks

Can RTX 4090 run Llama 3.3 70B Instruct?Can RTX 3090 run Qwen3 32B?Can M4 Max (40-core GPU, 128GB) run gpt-oss-120b (MoE)?Can RTX 5090 run Gemma 3 27B?Can RTX 4060 Ti 8GB run Llama 3.1 8B Instruct?Can M4 (10-core GPU, 24GB) run Qwen3 30B-A3B (MoE)?

Get new models & benchmarks in your inbox

No spam. Unsubscribe anytime by replying to any email.

No suitable GPU? Rent one by the hour on Vast.ai or RunPod (affiliate links).