community pool / model answer
GLM-5.2-Int4-Int8Mix
chat · QuantTrio/GLM-5.2-Int4-Int8Mix
30.6 tok/s · model median · 66 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| CMP 170HX 64GB ×10 | 4-bit | 29.7 tok/s | measured | 229 | - GB | 131,072 | vllm |
| CMP 170HX 64GB ×8 | 4-bit | 30.6 tok/s | measured | 291 | - GB | 131,072 | 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.