Downloads · 30 days
22
33% of all-time downloads
UI-Mate-27B-MLX-MXFP4
majentik/UI-Mate-27B-MLX-MXFP4
UI-Mate-27B-MLX-MXFP4 is a image-text-to-text model from majentik. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
MLX MXFP4 (mxfp4, group size 32) quantized variant of tencent/UI-Mate-27B (text tower quantized; vision tower and projector retained in BF16) for Apple silicon via mlx-lm.
All-time downloads
66
Public
Parameters
27.4B
15.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
Parameter types
How the weights are stored.
U3226.9B · 98%
Try a prompt
Base models
Model card
From the Hugging Face model README
UI-Mate-27B-MLX-MXFP4
MLX MXFP4 (mxfp4, group size 32) quantized variant of tencent/UI-Mate-27B (text tower quantized; vision tower and projector retained in BF16) for Apple silicon via mlx-lm.
Provenance
- Source: tencent/UI-Mate-27B @ revision
53543405c72b93775f831d7c7fce7c4d64972636(Apache-2.0 (upstreamLICENSE)). - Quantized with
mlx_lm.convert(mlx-lm 0.31.3): mxfp4, 4-bit, group size 32.
Smoke gate
Before upload this pack passed a deterministic coherence gate: greedy
48-token chat generation loaded through
mlx_lm.load, judged for emptiness, repetition loops, multi-script
gibberish, and special-token debris. Verdict: ok.
Usage
pip install mlx-lm
mlx_lm.generate --model majentik/UI-Mate-27B-MLX-MXFP4 --prompt "Hello"
Evaluation
| Benchmark | Score |
|---|---|
| arc_easy_acc | 0.6250 |
| hellaswag_acc | 0.5300 |
Available tiers
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Aug 20, 2026
- Updated
- Aug 21, 2026