🔌
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 DBRX 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 → | ~94.2 | yes | 309k | — |
| AMD Instinct MI325X → | ~62.5 | yes | 489k | — |
| NVIDIA H200 → | ~56.5 | yes | 166k | — |
| AMD Instinct MI300X 192GB → | ~55.2 | yes | 309k | ~$15,000 |
| Intel Gaudi 3 → | ~36 | yes | 129k | — |
| NVIDIA RTX PRO 6000 Blackwell → | ~21.1 | yes | 39k | ~$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 DBRX?▶
On GenAIList, 6 Datacenter GPU options can run DBRX at Q4 — the fastest is the NVIDIA B200 at ~94.2 tok/s.
How fast is DBRX on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~21.1 to ~94.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.