New: connect Claude & other AIs to GenAIList over MCP โ research the catalog and contribute to the shared knowledge base. Learn how โ
Run IDEFICS-80B 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 โ | ~155.4 | yes | 398k | โ |
| AMD Instinct MI325X โ | ~103.1 | yes | 577k | โ |
| NVIDIA H200 โ | ~93.2 | yes | 255k | โ |
| AMD Instinct MI300X 192GB โ | ~91.1 | yes | 398k | ~$15,000 |
| NVIDIA H100 SXM5 80GB โ | ~65.1 | yes | 83k | ~$30,000 |
| Intel Gaudi 3 โ | ~59.5 | yes | 218k | โ |
| NVIDIA A100 SXM4 80GB โ | ~39.6 | yes | 83k | ~$15,000 |
| NVIDIA H100 PCIe 80GB โ | ~38.8 | yes | 83k | ~$25,000 |
| NVIDIA A100 PCIe 80GB โ | ~37.6 | yes | 83k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell โ | ~34.8 | yes | 128k | ~$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 IDEFICS-80B?โถ
On GenAIList, 10 Datacenter GPU options can run IDEFICS-80B at Q4 โ the fastest is the NVIDIA B200 at ~155.4 tok/s.
How fast is IDEFICS-80B on Datacenter GPU hardware?โถ
Estimated generation speed ranges from ~34.8 to ~155.4 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.