Will this model run on your hardware?
Can I run Microsoft: Phi 4 locally?
- 15B parameters
- context up to 16K
- licence: mit
- Weights: microsoft/phi-4 · GGUF: MaziyarPanahi/phi-4-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 15.6 GB |
| Q6_K | 12.0 GB |
| Q5_K_M | 10.6 GB |
| Q4_K_M | 9.1 GB |
| Q3_K_M | 7.4 GB |
| Q2_K | 5.5 GB |
Run it locally
ollama run hf.co/MaziyarPanahi/phi-4-GGUF:Q4_K_M
llama serve -hf MaziyarPanahi/phi-4-GGUF:Q4_K_M
LM Studio: open MaziyarPanahi/phi-4-GGUF