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 SciBERT?
Yes — here's how fast and up to what context, with real measured numbers.
SciBERT on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2669k | 26545.5-31636.4 t/s | ~132.7-158.2 (slow) |
| Q8 | yes | 2671k | 53090.9-63272.7 t/s | ~265.5-316.4 (slow) |
| Q4 | yes | 2671k | 94805.2-112987 t/s | ~474-564.9 (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 SciBERT?▶
Yes. At Q4 it generates ~94805.2-112987 tok/s and fits up to 2671k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~474-564.9 tok/s.
How much context fits?▶
At Q4, up to about 2671k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.