community pool / model answer
gemma-3-4b-it
chat · google/gemma-3-4b-it
112.1 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| M3 Ultra 512GB | 4-bit | 127.2 tok/s | reported | 185 | - GB | 8,192 | llama.cpp |
| RTX 3060 12GB | 4-bit | 97 tok/s | reported | 1,063 | 4.9 GB | 4,608 | 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.