community pool / model answer
gemma-4-31B-v2-MLX-4bit
chat · jdfelo/gemma-4-31B-v2-MLX-4bit
33.4 tok/s · model median · 1 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| M5 Pro 48GB | 4-bit | 33.4 tok/s | reported | 596 | 34.2 GB | 2,048 | mlx |
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.