PH

phi 4 test

PhiGGUF by kokitakeishiUpdated 2025-01-28
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturephi3
Smallest quant4.9 GB
Quick answer

phi 4 test needs about 7.1 GB of memory at Q1_K (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.9 GB (Q1_K) to 5.6 GB.

phi 4 test is a 14.7B-parameter Phi model in GGUF format, quantized by kokitakeishi. Its trained context length is 16K tokens. The repository has 3 quant files, from 4.9 GB (Q1_K) to 5.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_K4.9 GB 7.1 GB
Fits Get file →
Q1_K4.9 GB 7.1 GB
Fits Get file →
—5.6 GB 7.8 GB
Tight Get file →

What GPU do you need for phi 4 test?

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 the main file (5.6 GB file, about 7.8 GB in use).

Which phi 4 test quant should you choose?

Q1_K (4.9 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is Q1_K at 4.9 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters14.7B
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized bykokitakeishi
FamilyPhi
Licensemit
Downloads (HF)18
Last updated2025-01-28

Frequently asked questions about phi 4 test

How much VRAM does phi 4 test need?

About 7.1 GB at Q1_K with an 8K context window. That is the 4.9 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 test on an 8 GB GPU?

Yes, with the smaller files: the 5.6 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of phi 4 test GGUF?

It depends on the quant: Q1_K is 4.9 GB, Q1_K is 4.9 GB, file is 5.6 GB.

What context length does phi 4 test 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 test GGUF?

The files are on Hugging Face in the kokitakeishi/phi-4-test 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 test 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.

Similar models

Browse all →

More from kokitakeishi

All by kokitakeishi →

More Phi models

All Phi →

Other medium models

All medium models →