community pool / model answer
GLM-5.3-Flash-tr3-4bpw
chat · brandonmusic/GLM-5.3-Flash-tr3-4bpw
82.6 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 256GB | 3-bit | 36.6 tok/s | reported | 875 | - GB | 32,768 | vllm |
| RTX PRO 6000 Blackwell 96GB ×2 | 3-bit | 128.6 tok/s | reported | 94 | - 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.