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 OpenPhenom-S/16?
Yes — here's how fast and up to what context, with real measured numbers.
OpenPhenom-S/16 on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2667k | 16400.3-19545.6 t/s | ~82-97.7 (slow) |
| Q8 | yes | 2670k | 32800.6-39091.1 t/s | ~164-195.5 (slow) |
| Q4 | yes | 2671k | 58572.5-69805.6 t/s | ~292.9-349 (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 OpenPhenom-S/16?▶
Yes. At Q4 it generates ~58572.5-69805.6 tok/s and fits up to 2671k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~292.9-349 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.