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 HiFi - NN?
Yes — here's how fast and up to what context, with real measured numbers.
HiFi - NN on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2672k | 973333.3-1160000 t/s | ~4866.7-5800 (slow) |
| Q8 | yes | 2672k | 1946666.7-2320000 t/s | ~9733.3-11600 (slow) |
| Q4 | yes | 2672k | 3476190.5-4142857.1 t/s | ~17381-20714.3 (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 HiFi - NN?▶
Yes. At Q4 it generates ~3476190.5-4142857.1 tok/s and fits up to 2672k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~17381-20714.3 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.