PH

phi 4 poc

PhiGGUF by kygbjsUpdated 2025-03-19
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturellama
Smallest quant8.9 GB
Quick answer

phi 4 poc 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 2 quants, from 8.9 GB (Q4_K_M) to 15.6 GB (Q8_0).

phi 4 poc is a 14.7B-parameter Phi model in GGUF format, quantized by kygbjs. Its trained context length is 16K tokens. The repository has 2 quant files, from 8.9 GB (Q4_K_M) to 15.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M8.9 GB 11.1 GB
Too big Get file →
Q8_015.6 GB 17.8 GB
Too big Get file →

What GPU do you need for phi 4 poc?

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 Q4_K_M (8.9 GB file, about 11.1 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 phi 4 poc quant should you choose?

Q4_K_M is the usual starting point for phi 4 poc: 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.

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 bykygbjs
FamilyPhi
Licenseapache-2.0
Downloads (HF)33
Last updated2025-03-19

Frequently asked questions about phi 4 poc

How much VRAM does phi 4 poc 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 poc 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 poc GGUF?

It depends on the quant: Q4_K_M is 8.9 GB, Q8_0 is 15.6 GB.

What context length does phi 4 poc 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 poc GGUF?

The files are on Hugging Face in the kygbjs/phi-4-poc 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 poc 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.

Other GGUFs of phi-4-unsloth-bnb-4bit

Similar models

Browse all →

More from kygbjs

All by kygbjs →

More Phi models

All Phi →

Other medium models

All medium models →