Skip to content

dealignai

Qwen3.8-27B-MXFP8-CRACK

dealignai/Qwen3.8-27B-MXFP8-CRACK

Qwen3.8-27B-MXFP8-CRACK is a image-text-to-text model from dealignai. 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.

[!IMPORTANT] Set your sampler explicitly: temperature=1.0, topp=0.95, topk=20. Stop tokens eostokenid = [248046, 248044]. Reasoning is on by default at xhigh; tiers xhigh (default) / medium / low via the chat template…

Downloads · 30 days

416

9% of all-time downloads

All-time downloads

4.8K

Public

Parameters

27.8B

28.8 GB on disk

Likes

13

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors28.8 GB · 100%

Parameter types

How the weights are stored.

U3227.6B · 100%

Try a prompt

Base models

Task
Image-Text-to-Text
Library
mlx
Type
qwen3_5
License
apache-2.0
Languages
en, zh
Created
Aug 15, 2026
Updated
Sep 4, 2026