🔌
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 (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) 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 → | ~67,181.5 | yes | 2671k | — |
| AMD Instinct MI325X → | ~44,594.6 | yes | 3569k | — |
| NVIDIA H200 → | ~40,308.9 | yes | 1955k | — |
| AMD Instinct MI300X 192GB → | ~39,391.9 | yes | 2671k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~28,132.2 | yes | 1099k | ~$30,000 |
| Intel Gaudi 3 → | ~25,714.3 | yes | 1772k | — |
| NVIDIA A100 SXM4 80GB → | ~17,122.9 | yes | 1099k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~16,795.4 | yes | 1099k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~16,249.5 | yes | 1099k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~15,048.6 | yes | 1323k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~8,061.8 | yes | 649k | ~$6,800 |
| NVIDIA L40S 48GB → | ~7,255.6 | yes | 649k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~6,421.6 | yes | 649k | ~$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 (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)?▶
On GenAIList, 13 Datacenter GPU options can run (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) at Q4 — the fastest is the NVIDIA B200 at ~67,181.5 tok/s.
How fast is (ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~6,421.6 to ~67,181.5 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.