Skip to content

majentik

Mistral-Medium-3.5-128B-MLX-4bit

majentik/Mistral-Medium-3.5-128B-MLX-4bit

Mistral-Medium-3.5-128B-MLX-4bit 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 other.

MLX 4bit (affine, group size 32) quantized variant of mistralai/Mistral-Medium-3.5-128B (text tower quantized; vision tower and projector retained in BF16; source checkpoint is FP8) for Apple silicon via mlx-lm.

Downloads · 30 days

195

35% of all-time downloads

All-time downloads

561

Public

Parameters

128B

85.8 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors85.7 GB · 100%

Parameter types

How the weights are stored.

U32123B · 97%

Try a prompt

Base models

Task
Image-Text-to-Text
Library
mlx
Type
mistral3
License
other
Created
Aug 11, 2026
Updated
Aug 15, 2026