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 GPT-1?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-1 on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2669k | 24957.3-29743.6 t/s | ~124.8-148.7 (slow) |
| Q8 | yes | 2671k | 49914.5-59487.2 t/s | ~249.6-297.4 (slow) |
| Q4 | yes | 2671k | 89133.1-106227.1 t/s | ~445.7-531.1 (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 GPT-1?▶
Yes. At Q4 it generates ~89133.1-106227.1 tok/s and fits up to 2671k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~445.7-531.1 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.