New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the NVIDIA B200 run S4?
Yes — here's how fast and up to what context, with real measured numbers.
S4 on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2665k | 11726.9-13975.9 t/s | ~58.6-69.9 (slow) |
| Q8 | yes | 2669k | 23453.8-27951.8 t/s | ~117.3-139.8 (slow) |
| Q4 | yes | 2670k | 41881.8-49913.9 t/s | ~209.4-249.6 (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 S4?▶
Yes. At Q4 it generates ~41881.8-49913.9 tok/s and fits up to 2670k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~209.4-249.6 tok/s.
How much context fits?▶
At Q4, up to about 2670k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.