PH

Phi 4 Trim

PhiGGUF by matrixportalxUpdated 2025-02-20
Download on Hugging Face
Parameters6.14B
Context16K
Layers15
Architecturellama
Smallest quant3.6 GB
Quick answer

Phi 4 Trim needs about 4.7 GB of memory at Q4_0 (a 3.6 GB file) with an 8K context window, so it fits on a 6 GB GPU.

Phi 4 Trim is a 6.14B-parameter Phi model in GGUF format, quantized by matrixportalx. Its trained context length is 16K tokens. The repository has 1 quant file, from 3.6 GB (Q4_0) to 3.6 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_03.6 GB 4.7 GB
Fits Get file →

What GPU do you need for Phi 4 Trim?

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: the best quant that fits is Q4_0 (3.6 GB file, about 4.7 GB in use).

Which Phi 4 Trim quant should you choose?

Q4_0 (3.6 GB) is the middle option in this repository. 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

Architecturellama
Parameters6.14B
Layers15
Trained context16,384 tokens
KV cache (fp16)75 KB per token

Source

Quantized bymatrixportalx
FamilyPhi
Downloads (HF)7
Last updated2025-02-20

Frequently asked questions about Phi 4 Trim

How much VRAM does Phi 4 Trim need?

About 4.7 GB at Q4_0 with an 8K context window. That is the 3.6 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 Trim on an 8 GB GPU?

Yes, with Q4_0: the 3.6 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 4 Trim GGUF?

It depends on the quant: Q4_0 is 3.6 GB.

What context length does Phi 4 Trim support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.6 GB at 8K and 1.3 GB at 16K.

Where can I download Phi 4 Trim GGUF?

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

Other GGUFs of Phi-4-Trim

Similar models

Browse all →

More from matrixportalx

All by matrixportalx →

More Phi models

All Phi →

Other small models

All small models →