Downloads · 30 days
2.2K
57% of all-time downloads
Qwen3.6-35B-A3B-DFlash2-4bit
mlx-community/Qwen3.6-35B-A3B-DFlash2-4bit
Qwen3.6-35B-A3B-DFlash2-4bit is a text generation model from mlx-community. 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.
The DFlash 2 draft model for Qwen3.6-35B-A3B, as a standard safetensors checkpoint with MLX affine 4-bit weights (group size 64).
All-time downloads
3.9K
Public
Parameters
526M
479 MB on disk
Likes
10
Public
Repo makeup
Click a slice to open those files.
.safetensors479 MB · 100%
Parameter types
How the weights are stored.
U32399M · 76%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.6-35B-A3B-DFlash2-4bit
The DFlash 2 draft model for Qwen3.6-35B-A3B, as a standard safetensors checkpoint with MLX affine 4-bit weights (group size 64).
Source and changes
- Source: the
draft/files ofincoai/Qwen3.6-35B-A3B-Splash, revision0f4714b2db37b5f3c42a10de07281e74f88e4adc(Apache-2.0). That package names its draft source asincoai/Qwen3.6-35B-A3B-DFlash2, revision8e713508f0bb02f03b5cb5cabbc8d9604f924be2. - The draft model was made by Inco AI. This repository is not published or endorsed by Inco AI.
- Changes: the Splash runtime storage (tiled q4 integers with bf16 scales and biases) was converted to row-major
MLX affine storage in one
model.safetensors, and aconfig.jsonwas written. The integers, scales and biases are moved bit for bit; no tensor was requantized (208 tensors). The original unquantized weights are not recovered. Mask token id and RoPE parameters come from the target's configuration.source.jsonlists the SHA-256 of every source file.
License
Apache-2.0, as the source package. See LICENSE.
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3
- License
- apache-2.0
- Created
- Sep 23, 2026
- Updated
- Sep 25, 2026