🔌
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 AREX Base on Datacenter GPU hardware
10 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA B200 → | ~101.9 | yes | 326k | — |
| AMD Instinct MI325X → | ~67.6 | yes | 506k | — |
| NVIDIA H200 → | ~61.1 | yes | 183k | — |
| AMD Instinct MI300X 192GB → | ~59.7 | yes | 326k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~42.7 | yes | 12k | ~$30,000 |
| Intel Gaudi 3 → | ~39 | yes | 146k | — |
| NVIDIA A100 SXM4 80GB → | ~26 | yes | 12k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~25.5 | yes | 12k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~24.6 | yes | 12k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~22.8 | yes | 56k | ~$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 AREX Base?▶
On GenAIList, 10 Datacenter GPU options can run AREX Base at Q4 — the fastest is the NVIDIA B200 at ~101.9 tok/s.
How fast is AREX Base on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~22.8 to ~101.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.