🔌
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 GLM-130B on Datacenter GPU hardware
6 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| NVIDIA B200 → | ~95.6 | yes | 312k | — |
| AMD Instinct MI325X → | ~63.5 | yes | 492k | — |
| NVIDIA H200 → | ~57.4 | yes | 169k | — |
| AMD Instinct MI300X 192GB → | ~56.1 | yes | 312k | ~$15,000 |
| Intel Gaudi 3 → | ~36.6 | yes | 133k | — |
| NVIDIA RTX PRO 6000 Blackwell → | ~21.4 | yes | 43k | ~$8,500 |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Datacenter GPU hardware runs GLM-130B?▶
On GenAIList, 6 Datacenter GPU options can run GLM-130B at Q4 — the fastest is the NVIDIA B200 at ~95.6 tok/s.
How fast is GLM-130B on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~21.4 to ~95.6 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.