community pool / model answer
GLM-5.3-Flash
chat · zai-org/GLM-5.3-Flash
148.4 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 256GB | 3-bit | 19.8 tok/s | reported | 367 | 105 GB | 1,000,000 | vllm |
| RTX PRO 6000 Blackwell 96GB ×2 | 3-bit | 171.9 tok/s | reported | 177 | 180.5 GB | 352,512 | vllm |
| RTX PRO 6000 Blackwell 96GB ×4 | 8-bit | 146.8 tok/s | reported | 90 | - GB | 2,048 | vllm |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.