🔌
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 ProGen2-base 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 → | ~16,267.8 | yes | 2666k | — |
| AMD Instinct MI325X → | ~10,798.4 | yes | 3564k | — |
| NVIDIA H200 → | ~9,760.7 | yes | 1950k | — |
| AMD Instinct MI300X 192GB → | ~9,538.6 | yes | 2666k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~6,812.1 | yes | 1094k | ~$30,000 |
| Intel Gaudi 3 → | ~6,226.6 | yes | 1767k | — |
| NVIDIA A100 SXM4 80GB → | ~4,146.2 | yes | 1094k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~4,066.9 | yes | 1094k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~3,934.8 | yes | 1094k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~3,644 | yes | 1318k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~1,952.1 | yes | 644k | ~$6,800 |
| NVIDIA L40S 48GB → | ~1,756.9 | yes | 644k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~1,555 | yes | 644k | ~$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 ProGen2-base?▶
On GenAIList, 13 Datacenter GPU options can run ProGen2-base at Q4 — the fastest is the NVIDIA B200 at ~16,267.8 tok/s.
How fast is ProGen2-base on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~1,555 to ~16,267.8 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.