🔌
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 CodeT5-large 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 → | ~16,141 | yes | 2666k | — |
| AMD Instinct MI325X → | ~10,714.3 | yes | 3564k | — |
| NVIDIA H200 → | ~9,684.6 | yes | 1950k | — |
| AMD Instinct MI300X 192GB → | ~9,464.3 | yes | 2666k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~6,759 | yes | 1094k | ~$30,000 |
| Intel Gaudi 3 → | ~6,178.1 | yes | 1767k | — |
| NVIDIA A100 SXM4 80GB → | ~4,113.9 | yes | 1094k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~4,035.3 | yes | 1094k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~3,904.1 | yes | 1094k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~3,615.6 | yes | 1318k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~1,936.9 | yes | 644k | ~$6,800 |
| NVIDIA L40S 48GB → | ~1,743.2 | yes | 644k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~1,542.9 | yes | 644k | ~$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 CodeT5-large?▶
On GenAIList, 13 Datacenter GPU options can run CodeT5-large at Q4 — the fastest is the NVIDIA B200 at ~16,141 tok/s.
How fast is CodeT5-large on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~1,542.9 to ~16,141 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.