🔌
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-10B 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 → | ~1,242.9 | yes | 1035k | — |
| AMD Instinct MI325X → | ~825 | yes | 1394k | — |
| NVIDIA H200 → | ~745.7 | yes | 748k | — |
| AMD Instinct MI300X 192GB → | ~728.8 | yes | 1035k | ~$15,000 |
| NVIDIA H100 SXM5 80GB → | ~520.4 | yes | 406k | ~$30,000 |
| Intel Gaudi 3 → | ~475.7 | yes | 675k | — |
| NVIDIA A100 SXM4 80GB → | ~316.8 | yes | 406k | ~$15,000 |
| NVIDIA H100 PCIe 80GB → | ~310.7 | yes | 406k | ~$25,000 |
| NVIDIA A100 PCIe 80GB → | ~300.6 | yes | 406k | ~$12,000 |
| NVIDIA RTX PRO 6000 Blackwell → | ~278.4 | yes | 496k | ~$8,500 |
| NVIDIA RTX 6000 Ada 48GB → | ~149.1 | yes | 226k | ~$6,800 |
| NVIDIA L40S 48GB → | ~134.2 | yes | 226k | ~$10,000 |
| AMD Radeon Pro W7900 48GB → | ~118.8 | yes | 226k | ~$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 GLM-10B?▶
On GenAIList, 13 Datacenter GPU options can run GLM-10B at Q4 — the fastest is the NVIDIA B200 at ~1,242.9 tok/s.
How fast is GLM-10B on Datacenter GPU hardware?▶
Estimated generation speed ranges from ~118.8 to ~1,242.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.