🔌
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 BiRNA-BERT 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 → | ~106,227.1 | yes | 2671k | — |
| AMD Instinct MI325X → | ~70,512.8 | yes | 3570k | — |
| NVIDIA H200 → | ~63,736.3 | yes | 1955k | — |
| AMD Instinct MI300X 192GB → | ~62,286.3 | yes | 2671k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~44,482.6 | yes | 1099k | ~$30,000 |
| Intel Gaudi 3 → | ~40,659.3 | yes | 1773k | — |
| NVIDIA A100 SXM4 80GB → | ~27,074.6 | yes | 1099k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~26,556.8 | yes | 1099k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~25,693.7 | yes | 1099k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~23,794.9 | yes | 1324k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~12,747.3 | yes | 650k | ~$6,800 |
| NVIDIA L40S 48GB → | ~11,472.5 | yes | 650k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~10,153.8 | yes | 650k | ~$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 BiRNA-BERT?▶
On GenAIList, 13 Datacenter GPU options can run BiRNA-BERT at Q4 — the fastest is the NVIDIA B200 at ~106,227.1 tok/s.
How fast is BiRNA-BERT on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~10,153.8 to ~106,227.1 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.