New: connect Claude & other AIs to GenAIList over MCP โ research the catalog and contribute to the shared knowledge base. Learn how โ
Run Distilled Grandmaster on Datacenter GPU hardware
13 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA B200 โ | ~46,031.7 | yes | 2670k | โ |
| AMD Instinct MI325X โ | ~30,555.6 | yes | 3569k | โ |
| NVIDIA H200 โ | ~27,619 | yes | 1954k | โ |
| AMD Instinct MI300X 192GB โ | ~26,990.7 | yes | 2670k | ~$15,000 |
| NVIDIA H100 SXM5 80GB โ | ~19,275.8 | yes | 1098k | ~$30,000 |
| Intel Gaudi 3 โ | ~17,619 | yes | 1772k | โ |
| NVIDIA A100 SXM4 80GB โ | ~11,732.3 | yes | 1098k | ~$15,000 |
| NVIDIA H100 PCIe 80GB โ | ~11,507.9 | yes | 1098k | ~$25,000 |
| NVIDIA A100 PCIe 80GB โ | ~11,133.9 | yes | 1098k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell โ | ~10,311.1 | yes | 1322k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB โ | ~5,523.8 | yes | 649k | ~$6,800 |
| NVIDIA L40S 48GB โ | ~4,971.4 | yes | 649k | ~$10,000 |
| AMD Radeon Pro W7900 48GB โ | ~4,400 | yes | 649k | ~$3,999 |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Datacenter GPU hardware runs Distilled Grandmaster?โถ
On GenAIList, 13 Datacenter GPU options can run Distilled Grandmaster at Q4 โ the fastest is the NVIDIA B200 at ~46,031.7 tok/s.
How fast is Distilled Grandmaster on Datacenter GPU hardware?โถ
Estimated generation speed ranges from ~4,400 to ~46,031.7 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.