Downloads · 30 days
67
47% of all-time downloads
Qwen3.5-4B-Text-MLX-4bit
droyster/Qwen3.5-4B-Text-MLX-4bit
Qwen3.5-4B-Text-MLX-4bit is a machine learning model from droyster. 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.
mlx-community/Qwen3.5-4B-MLX-4bit with the unused vision tower removed: 297 visiontower. tensors dropped, 924 language-model tensors kept, 2.9 GB → 2.2 GB download (−667 MB). Nothing else is changed.
All-time downloads
142
Public
Parameters
4.2B
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 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-Text-MLX-4bit
mlx-community/Qwen3.5-4B-MLX-4bit with the unused vision tower removed:
297 vision_tower.* tensors dropped, 924 language-model tensors kept,
2.9 GB → 2.2 GB download (−667 MB). Nothing else is changed.
mlx_lm's qwen3_5 loader already discards vision tensors before load
(sanitize()), so this republish is purely a download/disk win — runtime
behavior is identical. Verified: maximum absolute logit delta vs the
original model is exactly 0.0 on a fixed prompt; greedy argmax matches.
Built for faster-context, a local repository-retrieval subagent for Apple Silicon, where this is the default serving model (zero-shot, no fine-tuning).
Use
pip install mlx-lm
mlx_lm.generate --model droyster/Qwen3.5-4B-Text-MLX-4bit --prompt "hello"
Provenance
- Base: Alibaba Qwen3.5-4B (Apache-2.0), community 4-bit MLX conversion
mlx-community/Qwen3.5-4B-MLX-4bit. - This repo: same weights, vision tower stripped with MLX
(
mx.load→ filtervision_tower.*→mx.save_safetensors),vision_configremoved fromconfig.json. Tokenizer files unchanged.
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026