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 Hyena-2 153M?
Yes — here's how fast and up to what context, with real measured numbers.
Hyena-2 153M on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2668k | 19085-22745.1 t/s | ~95.4-113.7 (slow) |
| Q8 | yes | 2670k | 38169.9-45490.2 t/s | ~190.8-227.5 (slow) |
| Q4 | yes | 2671k | 68160.6-81232.5 t/s | ~340.8-406.2 (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 Hyena-2 153M?▶
Yes. At Q4 it generates ~68160.6-81232.5 tok/s and fits up to 2671k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~340.8-406.2 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.