PH

Phi 4 14B ULTRA

PhiGGUF by ia4youUpdated 2025-11-09
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturellama
Smallest quant8.9 GB
Quick answer

Phi 4 14B ULTRA needs about 11.1 GB of memory at its main file (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.9 GB to 10.4 GB.

Phi 4 14B ULTRA is a 14.7B-parameter Phi model in GGUF format, quantized by ia4you. Its trained context length is 16K tokens. The repository has 2 quant files, from 8.9 GB to 10.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.9 GB 11.1 GB
Too big Get file →
—10.4 GB 12.6 GB
Too big Get file →

What GPU do you need for Phi 4 14B ULTRA?

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 the main file (8.9 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (10.4 GB file, about 12.6 GB in use).

Specifications

Architecture from the GGUF header

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

Source

Quantized byia4you
FamilyPhi
Licensemit
Downloads (HF)58
Last updated2025-11-09

Frequently asked questions about Phi 4 14B ULTRA

How much VRAM does Phi 4 14B ULTRA need?

About 11.1 GB at its main file 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 14B ULTRA on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Phi 4 14B ULTRA GGUF?

It depends on the quant: file is 8.9 GB, file is 10.4 GB.

What context length does Phi 4 14B ULTRA 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 14B ULTRA GGUF?

The files are on Hugging Face in the ia4you/Phi-4-14B-ULTRA 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 14B ULTRA 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 Phi models

All Phi →

Other medium models

All medium models →