🔌
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 Llama Nemotron Super 49B 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 → | ~253.6 | yes | 451k | — |
| AMD Instinct MI325X → | ~168.4 | yes | 630k | — |
| NVIDIA H200 → | ~152.2 | yes | 308k | — |
| AMD Instinct MI300X 192GB → | ~148.7 | yes | 451k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~106.2 | yes | 136k | ~$30,000 |
| Intel Gaudi 3 → | ~97.1 | yes | 271k | — |
| NVIDIA A100 SXM4 80GB → | ~64.6 | yes | 136k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~63.4 | yes | 136k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~61.4 | yes | 136k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~56.8 | yes | 181k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~30.4 | yes | 46k | ~$6,800 |
| NVIDIA L40S 48GB → | ~27.4 | yes | 46k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~24.2 | yes | 46k | ~$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 Llama Nemotron Super 49B?▶
On GenAIList, 13 Datacenter GPU options can run Llama Nemotron Super 49B at Q4 — the fastest is the NVIDIA B200 at ~253.6 tok/s.
How fast is Llama Nemotron Super 49B on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~24.2 to ~253.6 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.