PH

Phi 4 Mini 6b Merge

PhiGGUF by Jonah-MUpdated 2025-06-29
Download on Hugging Face
Parameters6.25B
Context128K
Layers56
Architecturephi3
Smallest quant4.6 GB
Quick answer

Phi 4 Mini 6b Merge needs about 7.0 GB of memory at Q5_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Phi 4 Mini 6b Merge is a 6.25B-parameter Phi model in GGUF format, quantized by Jonah-M. Its trained context length is 128K tokens. The repository has 1 quant file, from 4.6 GB (Q5_K_M) to 4.6 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M4.6 GB 7.0 GB
Fits Get file →

What GPU do you need for Phi 4 Mini 6b Merge?

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 Q5_K_M (4.6 GB file, about 7.0 GB in use).

Which Phi 4 Mini 6b Merge quant should you choose?

Q5_K_M (4.6 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
Parameters6.25B
Layers56
Trained context131,072 tokens
KV cache (fp16)224 KB per token

Source

Quantized byJonah-M
FamilyPhi
Licensemit
Downloads (HF)20
Last updated2025-06-29

Frequently asked questions about Phi 4 Mini 6b Merge

How much VRAM does Phi 4 Mini 6b Merge need?

About 7.0 GB at Q5_K_M with an 8K context window. That is the 4.6 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 Mini 6b Merge on an 8 GB GPU?

Yes, with Q5_K_M: the 4.6 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 4 Mini 6b Merge GGUF?

It depends on the quant: Q5_K_M is 4.6 GB.

What context length does Phi 4 Mini 6b Merge support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Phi 4 Mini 6b Merge GGUF?

The files are on Hugging Face in the Jonah-M/Phi-4-mini-6b-merge-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.

What license does Phi 4 Mini 6b Merge 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.

Other GGUFs of Phi-4-mini-6b-merge

Similar models

Browse all →

More from Jonah-M

All by Jonah-M →

More Phi models

All Phi →

Other small models

All small models →