community pool / model answer
Llama-3.2-3B-Instruct
chat · meta-llama/Llama-3.2-3B-Instruct
75.9 tok/s · model median · 44 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| M1 Max 64GB | 16-bit | 50.9 tok/s | reported | - | - GB | 640 | llama.cpp |
| RTX 3060 12GB | 4-bit | 95.8 tok/s | measured | 681 | - GB | 131,072 | llama.cpp |
| RX 6700 XT 12GB | 16-bit | 48.3 tok/s | measured | - | - GB | 4,736 | 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.