🔌
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 B200 run Qwen2.5-32B?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen2.5-32B on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 420k | 89.8-107.1 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 544k | 179.7-214.2 t/s | ~0.9-1.1 (slow) |
| Q4 | yes | 599k | 320.9-382.4 t/s | ~1.6-1.9 (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 B200 run Qwen2.5-32B?▶
Yes. At Q4 it generates ~320.9-382.4 tok/s and fits up to 599k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.6-1.9 tok/s.
How much context fits?▶
At Q4, up to about 599k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.