Downloads · 30 days
66
9% of all-time downloads
Qwen3.6-35B-A3B-4.4bit-msq
mlx-community/Qwen3.6-35B-A3B-4.4bit-msq
Qwen3.6-35B-A3B-4.4bit-msq is a image-text-to-text model from mlx-community. 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 transformers. The card lists the license as apache-2.0.
Mixed-precision MLX quantization of Qwen/Qwen3.6-35B-A3B, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assign…
All-time downloads
764
Public
Parameters
35.1B
21.2 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors21.2 GB · 100%
Parameter types
How the weights are stored.
U324.7B · 79%
Try a prompt
Model card
From the Hugging Face model README
Qwen3.6-35B-A3B — MLX 4.4 BPW
Mixed-precision MLX quantization of Qwen/Qwen3.6-35B-A3B, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.
Details
- Type: Vision (VLM)
- Average: 4.39 bits per weight
- Method: MLX Smart Quantize (MSQ)
- AWQ scaling: applied to 50 groups
Evaluation
| Benchmark | Score | Samples |
|---|---|---|
| MMLU | 81.8% | 285 |
| HellaSwag | 91.5% | 200 |
| GSM8K | 87% | 200 |
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5_moe
- License
- apache-2.0
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026