🔌
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 CodeGen-Mono 16.1B 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 → | ~772 | yes | 634k | — |
| AMD Instinct MI325X → | ~512.4 | yes | 858k | — |
| NVIDIA H200 → | ~463.2 | yes | 455k | — |
| AMD Instinct MI300X 192GB → | ~452.6 | yes | 634k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~323.3 | yes | 241k | ~$30,000 |
| Intel Gaudi 3 → | ~295.5 | yes | 409k | — |
| NVIDIA A100 SXM4 80GB → | ~196.8 | yes | 241k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~193 | yes | 241k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~186.7 | yes | 241k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~172.9 | yes | 297k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~92.6 | yes | 128k | ~$6,800 |
| NVIDIA L40S 48GB → | ~83.4 | yes | 128k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~73.8 | yes | 128k | ~$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 CodeGen-Mono 16.1B?▶
On GenAIList, 13 Datacenter GPU options can run CodeGen-Mono 16.1B at Q4 — the fastest is the NVIDIA B200 at ~772 tok/s.
How fast is CodeGen-Mono 16.1B on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~73.8 to ~772 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.