🔌
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 T0-XXL 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 → | ~1,129.9 | yes | 1031k | — |
| AMD Instinct MI325X → | ~750 | yes | 1391k | — |
| NVIDIA H200 → | ~677.9 | yes | 745k | — |
| AMD Instinct MI300X 192GB → | ~662.5 | yes | 1031k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~473.1 | yes | 402k | ~$30,000 |
| Intel Gaudi 3 → | ~432.5 | yes | 672k | — |
| NVIDIA A100 SXM4 80GB → | ~288 | yes | 402k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~282.5 | yes | 402k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~273.3 | yes | 402k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~253.1 | yes | 492k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~135.6 | yes | 223k | ~$6,800 |
| NVIDIA L40S 48GB → | ~122 | yes | 223k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~108 | yes | 223k | ~$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 T0-XXL?▶
On GenAIList, 13 Datacenter GPU options can run T0-XXL at Q4 — the fastest is the NVIDIA B200 at ~1,129.9 tok/s.
How fast is T0-XXL on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~108 to ~1,129.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.