New: connect Claude & other AIs to GenAIList over MCP โ research the catalog and contribute to the shared knowledge base. Learn how โ
Run FvFold 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 โ | ~1,349,495.9 | yes | 2672k | โ |
| AMD Instinct MI325X โ | ~895,786.1 | yes | 3571k | โ |
| NVIDIA H200 โ | ~809,697.6 | yes | 1956k | โ |
| AMD Instinct MI300X 192GB โ | ~791,277.7 | yes | 2672k | ~$15,000 |
| NVIDIA H100 SXM5 80GB โ | ~565,101.4 | yes | 1100k | ~$30,000 |
| Intel Gaudi 3 โ | ~516,531.2 | yes | 1774k | โ |
| NVIDIA A100 SXM4 80GB โ | ~343,952.8 | yes | 1100k | ~$15,000 |
| NVIDIA H100 PCIe 80GB โ | ~337,374 | yes | 1100k | ~$25,000 |
| NVIDIA A100 PCIe 80GB โ | ~326,409.3 | yes | 1100k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell โ | ~302,287.1 | yes | 1325k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB โ | ~161,939.5 | yes | 651k | ~$6,800 |
| NVIDIA L40S 48GB โ | ~145,745.6 | yes | 651k | ~$10,000 |
| AMD Radeon Pro W7900 48GB โ | ~128,993.2 | yes | 651k | ~$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 FvFold?โถ
On GenAIList, 13 Datacenter GPU options can run FvFold at Q4 โ the fastest is the NVIDIA B200 at ~1,349,495.9 tok/s.
How fast is FvFold on Datacenter GPU hardware?โถ
Estimated generation speed ranges from ~128,993.2 to ~1,349,495.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.