🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the NVIDIA B200 run ProGen2-xlarge?
Yes — here's how fast and up to what context, with real measured numbers.
ProGen2-xlarge on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1239k | 456.3-543.8 t/s | ~2.3-2.7 (slow) |
| Q8 | yes | 1287k | 912.5-1087.5 t/s | ~4.6-5.4 (slow) |
| Q4 | yes | 1309k | 1629.5-1942 t/s | ~8.1-9.7 (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 ProGen2-xlarge?▶
Yes. At Q4 it generates ~1629.5-1942 tok/s and fits up to 1309k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~8.1-9.7 tok/s.
How much context fits?▶
At Q4, up to about 1309k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.