MA

UI Mate 27B

MateGGUF by starchickenUpdated 2026-08-20
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant16.5 GB
Quick answer

UI Mate 27B needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 16.5 GB (Q4_K_M) to 22.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

UI Mate 27B – a 27B‑parameter GUI agent for long‑horizon desktop tasks

UI Mate 27B is an open‑weight foundation GUI agent based on Qwen3.6‑27B. It observes live screenshots, reasons over the visible state, and produces structured keyboard and mouse actions. The model supports reasoning, tools, and vision.

Good at

  • Long‑horizon GUI task execution
  • Structured action generation for pyautogui
  • Live‑screen grounding

Limits

  • No vision support in llama.cpp without the mmproj projector
  • Requires 8k context for full performance
  • License is Apache‑2.0

Best for

  • Automating desktop workflows
  • Testing GUI applications
  • Building custom desktop agents

Who it’s for. Developers and researchers building autonomous desktop agents or testing GUI automation. The model is suitable for those who need structured action outputs and live‑screen reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 16.55 GB, estimated 19.2 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (19.23 GB, 21.9 GB). For 16 GB VRAM use Q6_K (22.08 GB, 24.7 GB). Estimates are approximate.

What GPU do you need for UI Mate 27B?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.1 GB file, about 24.7 GB in use).

Which UI Mate 27B quant should you choose?

Q4_K_M is the usual starting point for UI Mate 27B: it balances file size and quality well. Here it is a 16.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bystarchicken
FamilyMate
Licenseapache-2.0
Downloads (HF)630
Last updated2026-08-20

Frequently asked questions about UI Mate 27B

How much VRAM does UI Mate 27B need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 UI Mate 27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of UI Mate 27B GGUF?

It depends on the quant: Q4_K_M is 16.5 GB, Q5_K_M is 19.2 GB, Q6_K is 22.1 GB.

What context length does UI Mate 27B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download UI Mate 27B GGUF?

The files are on Hugging Face in the starchicken/UI-Mate-27B-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 UI Mate 27B 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.

Can I run UI Mate 27B on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 19.2 GB memory at 8k context, which is within 8 GB VRAM when using GPU memory swapping.

Does the model support vision in llama.cpp?

Vision support requires the mmproj projector included in the GGUF file; llama.cpp must be built with qwen3_5 / Gated DeltaNet support.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of UI-Mate-27B

Similar models

Browse all →

More Mate models

All Mate →

Other medium models

All medium models →