Microsoft · open-weights model
Phi-4
Phi-4 is a 14.7B-parameter model by Microsoft. Its smallest quant (Q4_K_M) needs at least 11.2GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 36 of the 50 machines we track.
- Parameters
- 14.7B
- Layers
- 40
- Max context
- 16K
- Attention
- GQA
- License
- mit
Config from microsoft/phi-4
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 15.6 GB | 17.8 GB |
| Q6_K | 12.0 GB | 14.2 GB |
| Q5_K_M | 10.6 GB | 12.8 GB |
| Q4_K_M | 9.1 GB | 11.2 GB |
What runs Phi-4
Every machine we track, graded at its best clean-fit quant.
Verdicts computed from published specs and measured GGUF sizes — how the math works.