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 ESM1-670M (UR100)?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1-670M (UR100) on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2652k | 4363.4-5200.2 t/s | ~21.8-26 (slow) |
| Q8 | yes | 2662k | 8726.8-10400.5 t/s | ~43.6-52 (slow) |
| Q4 | yes | 2667k | 15583.6-18572.3 t/s | ~77.9-92.9 (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 ESM1-670M (UR100)?▶
Yes. At Q4 it generates ~15583.6-18572.3 tok/s and fits up to 2667k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~77.9-92.9 tok/s.
How much context fits?▶
At Q4, up to about 2667k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.