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 2 (bio)?
Yes — here's how fast and up to what context, with real measured numbers.
Genie 2 (bio) on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2672k | 185987.3-221656.1 t/s | ~929.9-1108.3 (slow) |
| Q8 | yes | 2672k | 371974.5-443312.1 t/s | ~1859.9-2216.6 (slow) |
| Q4 | yes | 2672k | 664240.2-791628.8 t/s | ~3321.2-3958.1 (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 2 (bio)?▶
Yes. At Q4 it generates ~664240.2-791628.8 tok/s and fits up to 2672k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3321.2-3958.1 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.