Downloads · 30 days
27
3% of all-time downloads
Qwen3.5-35B-A3B-MLX-oQ4-FP16
deepsweet/Qwen3.5-35B-A3B-MLX-oQ4-FP16
Qwen3.5-35B-A3B-MLX-oQ4-FP16 is a text generation model from deepsweet. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
This model was converted to MLX format from Qwen/Qwen3.5-35B-A3B using:
All-time downloads
828
Public
Parameters
34.7B
20.3 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors20.3 GB · 100%
Parameter types
How the weights are stored.
U3234.6B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
This model was converted to MLX format from Qwen/Qwen3.5-35B-A3B using:
- oMLX v0.36.0
- specific optimization for M1/M2 Apple Silicon performance, see jundot/omlx/issues/604 for more details and benchmarks
- fully fixed
chat_template.jinjaby @froggeric
Settings:
- Level: oQ4
- Sensitivity model: Qwen3.5-35B-A3B-MLX-MXFP4-FP16
- Text Only: yes
- Non-quant weight dtype: float16
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5_moe
- License
- apache-2.0
- Languages
- en
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026