🔌
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 Baize-v2-13B (白泽) 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 → | ~956 | yes | 1025k | — |
| AMD Instinct MI325X → | ~634.6 | yes | 1384k | — |
| NVIDIA H200 → | ~573.6 | yes | 738k | — |
| AMD Instinct MI300X 192GB → | ~560.6 | yes | 1025k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~400.3 | yes | 396k | ~$30,000 |
| Intel Gaudi 3 → | ~365.9 | yes | 665k | — |
| NVIDIA A100 SXM4 80GB → | ~243.7 | yes | 396k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~239 | yes | 396k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~231.2 | yes | 396k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~214.2 | yes | 485k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~114.7 | yes | 216k | ~$6,800 |
| NVIDIA L40S 48GB → | ~103.3 | yes | 216k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~91.4 | yes | 216k | ~$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 Baize-v2-13B (白泽)?▶
On GenAIList, 13 Datacenter GPU options can run Baize-v2-13B (白泽) at Q4 — the fastest is the NVIDIA B200 at ~956 tok/s.
How fast is Baize-v2-13B (白泽) on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~91.4 to ~956 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.