New: connect Claude & other AIs to GenAIList over MCP โ research the catalog and contribute to the shared knowledge base. Learn how โ
Run Stockmark-13B 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 | ~941.6 | yes | 1024k | โ |
| AMD Instinct MI325X โ | ~625 | yes | 1383k | โ |
| NVIDIA H200 โ | ~564.9 | yes | 737k | โ |
| AMD Instinct MI300X 192GB โ | ~552.1 | yes | 1024k | ~$15,000 |
| NVIDIA H100 SXM5 80GB โ | ~394.3 | yes | 395k | ~$30,000 |
| Intel Gaudi 3 โ | ~360.4 | yes | 664k | โ |
| NVIDIA A100 SXM4 80GB โ | ~240 | yes | 395k | ~$15,000 |
| NVIDIA H100 PCIe 80GB โ | ~235.4 | yes | 395k | ~$25,000 |
| NVIDIA A100 PCIe 80GB โ | ~227.7 | yes | 395k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell โ | ~210.9 | yes | 485k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB โ | ~113 | yes | 215k | ~$6,800 |
| NVIDIA L40S 48GB โ | ~101.7 | yes | 215k | ~$10,000 |
| AMD Radeon Pro W7900 48GB โ | ~90 | yes | 215k | ~$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 Stockmark-13B?โถ
On GenAIList, 13 Datacenter GPU options can run Stockmark-13B at Q4 โ the fastest is the NVIDIA B200 at ~941.6 tok/s.
How fast is Stockmark-13B on Datacenter GPU hardware?โถ
Estimated generation speed ranges from ~90 to ~941.6 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.