community pool / model answer
gemma-4-31B-it-qat-GGUF
chat · unsloth/gemma-4-31B-it-qat-GGUF
22.5 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| M5 Pro 24GB | 4-bit | 27.8 tok/s | reported | 691 | - GB | 8,192 | llama.cpp |
| RTX 5090 32GB | 4-bit | 207.6 tok/s | reported | 78 | 30.2 GB | 200,000 | llama.cpp |
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.