Phi4 needs about 11.1 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 8.4 GB (Q4_0) to 15.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.
Phi4 is a 14.7B-parameter Phi model in GGUF format, quantized by AlSamCur123. Its trained context length is 32K tokens. The repository has 5 quant files, from 8.4 GB (Q4_0) to 15.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_M | 8.9 GB | 11.1 GB | Too big | Get file → | |
| Q5_K_M | 10.4 GB | 12.6 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 14.2 GB | Too big | Get file → | |
| Q8_0 | 15.6 GB | 17.8 GB | Too big | Get file → |
What GPU do you need for Phi4?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q4_K_M (8.9 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.6 GB file, about 17.8 GB in use).
Which Phi4 quant should you choose?
Q4_K_M is the usual starting point for Phi4: it balances file size and quality well. Here it is a 8.9 GB file.
The Q8_0 file is 15.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q4_0 at 8.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Phi4
How much VRAM does Phi4 need?
About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Phi4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Phi4 GGUF?
It depends on the quant: Q4_0 is 8.4 GB, Q4_K_M is 8.9 GB, Q5_K_M is 10.4 GB, Q6_K is 12.0 GB, Q8_0 is 15.6 GB.
What context length does Phi4 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.
Where can I download Phi4 GGUF?
The files are on Hugging Face in the AlSamCur123/Phi4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Phi4 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.