🔌
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 Stable LM 2 12B 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 → | ~1,023.5 | yes | 1027k | — |
| AMD Instinct MI325X → | ~679.4 | yes | 1387k | — |
| NVIDIA H200 → | ~614.1 | yes | 741k | — |
| AMD Instinct MI300X 192GB → | ~600.1 | yes | 1027k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~428.6 | yes | 399k | ~$30,000 |
| Intel Gaudi 3 → | ~391.7 | yes | 668k | — |
| NVIDIA A100 SXM4 80GB → | ~260.9 | yes | 399k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~255.9 | yes | 399k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~247.6 | yes | 399k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~229.3 | yes | 488k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~122.8 | yes | 219k | ~$6,800 |
| NVIDIA L40S 48GB → | ~110.5 | yes | 219k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~97.8 | yes | 219k | ~$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 Stable LM 2 12B?▶
On GenAIList, 13 Datacenter GPU options can run Stable LM 2 12B at Q4 — the fastest is the NVIDIA B200 at ~1,023.5 tok/s.
How fast is Stable LM 2 12B on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~97.8 to ~1,023.5 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.