community pool / model answer
Mellum2-12B-A2.5B-Instruct
chat · JetBrains/Mellum2-12B-A2.5B-Instruct
62.7 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RX 570 4GB ×2 | 4-bit | 62.7 tok/s | reported | 95 | - GB | 2,048 | 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.