MI

MiniCPM o 4 5

MiniCPMGGUF by orca-zhangUpdated 2026-08-26
Download on Hugging Face
Parameters527M
Context—
Layers—
Architectureclip
Smallest quant0.7 GB
Quick answer

MiniCPM o 4 5 needs about 1.3 GB of memory at Q6_K (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.

MiniCPM o 4 5 is a 527M-parameter MiniCPM model in GGUF format, quantized by orca-zhang. The repository has 1 quant file, from 0.7 GB (Q6_K) to 0.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K0.7 GB 1.3 GB
Fits Get file →

What GPU do you need for MiniCPM o 4 5?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q6_K (0.7 GB file, about 1.3 GB in use).

Which MiniCPM o 4 5 quant should you choose?

Q6_K (0.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureclip
Parameters527M

Source

Quantized byorca-zhang
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)14
Last updated2026-08-26

Frequently asked questions about MiniCPM o 4 5

How much VRAM does MiniCPM o 4 5 need?

About 1.3 GB at Q6_K with an 8K context window. That is the 0.7 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 MiniCPM o 4 5 on an 8 GB GPU?

Yes, with Q6_K: the 0.7 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniCPM o 4 5 GGUF?

It depends on the quant: Q6_K is 0.7 GB.

Where can I download MiniCPM o 4 5 GGUF?

The files are on Hugging Face in the orca-zhang/MiniCPM-o-4_5-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 MiniCPM o 4 5 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.

Similar models

Browse all →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →