Downloads · 30 days
455
19% of all-time downloads
Qwen3.8-27B-MLX-2bit
majentik/Qwen3.8-27B-MLX-2bit
Qwen3.8-27B-MLX-2bit 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 2bit (affine, group size 32) quantized variant of Qwen/Qwen3.8-27B (text tower quantized; vision tower and projector retained in BF16) for Apple silicon via mlx-lm.
All-time downloads
2.4K
Public
Parameters
27.4B
11 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors11 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
Qwen3.8-27B-MLX-2bit
MLX 2bit (affine, group size 32) quantized variant of Qwen/Qwen3.8-27B (text tower quantized; vision tower and projector retained in BF16) for Apple silicon via mlx-lm.
Provenance
- Source: Qwen/Qwen3.8-27B @ revision
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0(Apache-2.0 (upstreamLICENSE)). - Quantized with
mlx_lm.convert(mlx-lm 0.31.3): affine, 2-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/Qwen3.8-27B-MLX-2bit --prompt "Hello"
Evaluation
| Benchmark | Score |
|---|---|
| arc_easy_acc | 0.4900 |
| hellaswag_acc | 0.4100 |
License
Apache-2.0 — see the upstream LICENSE file in Qwen/Qwen3.8-27B.
Available tiers
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Aug 14, 2026
- Updated
- Aug 15, 2026