🔌
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 gpt-oss-20b?
Yes — here's how fast and up to what context, with real measured numbers.
gpt-oss-20b on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 509k | 139.6-166.4 t/s | ~0.7-0.8 (slow) |
| Q8 | yes | 588k | 279.3-332.9 t/s | ~1.4-1.7 (slow) |
| Q4 | yes | 623k | 498.7-594.4 t/s | ~2.5-3 (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 gpt-oss-20b?▶
Yes. At Q4 it generates ~498.7-594.4 tok/s and fits up to 623k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.5-3 tok/s.
How much context fits?▶
At Q4, up to about 623k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.