PH

phi 4 GGUF imatrix

PhiGGUF by mcm07Updated 2025-02-03
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

phi 4 GGUF imatrix 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 7 quants, from 4.8 GB (IQ2_S) to 8.9 GB (Q4_K_M).

phi 4 GGUF imatrix is a 14.7B-parameter Phi model in GGUF format, quantized by mcm07. Its trained context length is 16K tokens. The repository has 7 quant files, from 4.8 GB (IQ2_S) to 8.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_S4.8 GB 7.0 GB
Fits Get file →
IQ3_XS6.2 GB 8.4 GB
Too big Get file →
IQ4_XS8.0 GB 10.2 GB
Too big Get file →
—8.0 GB 10.2 GB
Too big Get file →
IQ4_NL8.4 GB 10.6 GB
Too big Get file →
IQ4_NL8.4 GB 10.6 GB
Too big Get file →
Q4_K_M8.9 GB 11.1 GB
Too big Get file →

What GPU do you need for phi 4 GGUF imatrix?

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: the best quant that fits is IQ2_S (4.8 GB file, about 7.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (8.9 GB file, about 11.1 GB in use).

Which phi 4 GGUF imatrix quant should you choose?

Q4_K_M is the usual starting point for phi 4 GGUF imatrix: it balances file size and quality well. Here it is a 8.9 GB file.

If memory is tight, the smallest file is IQ2_S at 4.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters14.7B
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymcm07
FamilyPhi
Base modelmicrosoft/phi-4
Licensemit
Downloads (HF)23
Last updated2025-02-03

Frequently asked questions about phi 4 GGUF imatrix

How much VRAM does phi 4 GGUF imatrix 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 phi 4 GGUF imatrix on an 8 GB GPU?

Yes, with IQ2_S: the 4.8 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi 4 GGUF imatrix GGUF?

It depends on the quant: IQ2_S is 4.8 GB, IQ3_XS is 6.2 GB, IQ4_XS is 8.0 GB, file is 8.0 GB, IQ4_NL is 8.4 GB, IQ4_NL is 8.4 GB and 1 more.

What context length does phi 4 GGUF imatrix support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.

Where can I download phi 4 GGUF imatrix GGUF?

The files are on Hugging Face in the mcm07/phi-4-GGUF-imatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does phi 4 GGUF imatrix use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of phi-4

Similar models

Browse all →

More Phi models

All Phi →

Other medium models

All medium models →