GPU requirement sizing
Start with just a model name — we fill the rest, then let you tune every assumption.
Popular models: Llama 3.1, Mistral, Qwen 2.5, Gemma 2 — type to autocomplete
141 GB · 4.8 TB/s · 989 TFLOPS
Based on your configuration — ISL 2,048, OSL 128, TTFT target 1.0s.