community pool / model answer
phi-4
chat · microsoft/phi-4
36 tok/s · model median · 3 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | 4-bit | 36 tok/s | reported | - | 8.7 GB | 2,048 | ollama |
| RTX 3080 12GB | 4-bit | 77 tok/s | reported | - | 8.7 GB | 2,048 | llama.cpp |
| RTX3060+RTX2080-pooled-20GB 20GB | 4-bit | 36 tok/s | reported | - | 8.7 GB | 2,048 | ollama |
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.