PH

Phi Mini MoE

PhiGGUF by noctrexUpdated 2025-10-27
Download on Hugging Face
Parameters7.65B
Context4K
Layers32
Architecturephimoe
Smallest quant4.9 GB
Quick answer

Phi Mini MoE needs about 6.5 GB of memory at MXFP4_MOE (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU.

Phi Mini MoE is a 7.65B-parameter Phi model in GGUF format, quantized by noctrex. Its trained context length is 4K tokens. The repository has 1 quant file, from 4.9 GB (MXFP4_MOE) to 4.9 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE4.9 GB 6.0 GB
Fits Get file →

What GPU do you need for Phi Mini MoE?

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 MXFP4_MOE (4.9 GB file, about 6.5 GB in use).

Which Phi Mini MoE quant should you choose?

MXFP4_MOE (4.9 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephimoe
Parameters7.65B (approximate, mixture of experts)
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized bynoctrex
FamilyPhi
Licensemit
Downloads (HF)32
Last updated2025-10-27

Frequently asked questions about Phi Mini MoE

How much VRAM does Phi Mini MoE need?

About 6.5 GB at MXFP4_MOE with an 8K context window. That is the 4.9 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 Mini MoE on an 8 GB GPU?

Yes, with MXFP4_MOE: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi Mini MoE GGUF?

It depends on the quant: MXFP4_MOE is 4.9 GB.

What context length does Phi Mini MoE support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download Phi Mini MoE GGUF?

The files are on Hugging Face in the noctrex/Phi-mini-MoE-instruct-MXFP4_MOE-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 Mini MoE 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-mini-MoE-instruct

Similar models

Browse all →

More from noctrex

All by noctrex →

More Phi models

All Phi →

Other small models

All small models →