Downloads · 30 days
93
100% of all-time downloads
Qwen3.5-4B-6bit-text
RuiSumida/Qwen3.5-4B-6bit-text
Qwen3.5-4B-6bit-text is a machine learning model from RuiSumida. Use it for the machine learning 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.
The weights of mlx-community/Qwen3.5-4B-6bit with the vision tower removed.
All-time downloads
93
Public
Parameters
4.2B
3.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.4 GB · 99%
Parameter types
How the weights are stored.
U324.2B · 100%
Base models
Model card
From the Hugging Face model README
Qwen3.5-4B-6bit, text-only
The weights of mlx-community/Qwen3.5-4B-6bit with the vision tower removed.
- All 924
language_model.*tensors are byte-identical to the source (verified withmx.array_equalafter re-saving). - The 297
vision_tower.*tensors (667 MB) are dropped. mlx-swift-lm's textQwen35model discards those keys on load anyway, so text generation is unchanged; this repack only saves the download and disk space (4.09 GB → 3.42 GB). config.json, tokenizer files andchat_template.jinjaare copied unchanged. Image input is not supported.
Built for the Luke iPhone app (on-device chat, MLX).
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Sep 19, 2026
- Updated
- Sep 19, 2026