🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the NVIDIA H200 run Qwen-72B?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen-72B on the NVIDIA H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | no | — | — | — |
| Q8 | yes | 172k | 48.7-58 t/s | ~0.4-0.5 (slow) |
| Q4 | yes | 268k | 86.9-103.6 t/s | ~0.7-0.9 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA H200 run Qwen-72B?▶
Yes. At Q4 it generates ~86.9-103.6 tok/s and fits up to 268k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.7-0.9 tok/s.
How much context fits?▶
At Q4, up to about 268k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.