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 OntoProtein?
Yes — here's how fast and up to what context, with real measured numbers.
OntoProtein on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2660k | 6952.4-8285.7 t/s | ~34.8-41.4 (slow) |
| Q8 | yes | 2666k | 13904.8-16571.4 t/s | ~69.5-82.9 (slow) |
| Q4 | yes | 2669k | 24829.9-29591.8 t/s | ~124.1-148 (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 OntoProtein?▶
Yes. At Q4 it generates ~24829.9-29591.8 tok/s and fits up to 2669k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~124.1-148 tok/s.
How much context fits?▶
At Q4, up to about 2669k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.