PH

phi 4 Q5 K M

PhiGGUF by pipilokUpdated 2024-12-15
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturephi3
Smallest quant10.6 GB
Quick answer

phi 4 Q5 K M needs about 12.8 GB of memory at Q5_K_M (a 10.6 GB file) with an 8K context window, so it fits on a 16 GB GPU.

phi 4 Q5 K M is a 14.7B-parameter Phi model in GGUF format, quantized by pipilok. Its trained context length is 16K tokens. The repository has 1 quant file, from 10.6 GB (Q5_K_M) to 10.6 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M10.6 GB 12.8 GB
Too big Get file →

What GPU do you need for phi 4 Q5 K M?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q5_K_M (10.6 GB file, about 12.8 GB in use).

Which phi 4 Q5 K M quant should you choose?

Q5_K_M (10.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

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 bypipilok
FamilyPhi
Downloads (HF)23
Last updated2024-12-15

Frequently asked questions about phi 4 Q5 K M

How much VRAM does phi 4 Q5 K M need?

About 12.8 GB at Q5_K_M with an 8K context window. That is the 10.6 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 Q5 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phi 4 Q5 K M GGUF?

It depends on the quant: Q5_K_M is 10.6 GB.

What context length does phi 4 Q5 K M 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 Q5 K M GGUF?

The files are on Hugging Face in the pipilok/phi-4_Q5_K_M-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

Similar models

Browse all →

More from pipilok

All by pipilok →

More Phi models

All Phi →

Other medium models

All medium models →