🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN ON DATACENTER GPU
Run dots.llm1 on Datacenter GPU hardware
6 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA B200 → | ~87.5 | yes | 292k | — |
| AMD Instinct MI325X → | ~58.1 | yes | 471k | — |
| NVIDIA H200 → | ~52.5 | yes | 149k | — |
| AMD Instinct MI300X 192GB → | ~51.3 | yes | 292k | ~$15,000 |
| Intel Gaudi 3 → | ~33.5 | yes | 112k | — |
| NVIDIA RTX PRO 6000 Blackwell → | ~19.6 | yes | 22k | ~$8,500 |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Datacenter GPU hardware runs dots.llm1?▶
On GenAIList, 6 Datacenter GPU options can run dots.llm1 at Q4 — the fastest is the NVIDIA B200 at ~87.5 tok/s.
How fast is dots.llm1 on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~19.6 to ~87.5 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.