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 Genie-SCOPe (bio)?
Yes — here's how fast and up to what context, with real measured numbers.
Genie-SCOPe (bio) on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2672k | 712195.1-848780.5 t/s | ~3561-4243.9 (slow) |
| Q8 | yes | 2672k | 1424390.2-1697561 t/s | ~7122-8487.8 (slow) |
| Q4 | yes | 2672k | 2543554-3031358.9 t/s | ~12717.8-15156.8 (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 Genie-SCOPe (bio)?▶
Yes. At Q4 it generates ~2543554-3031358.9 tok/s and fits up to 2672k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~12717.8-15156.8 tok/s.
How much context fits?▶
At Q4, up to about 2672k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.