Qwen3.5-4B-thinking-mlx-8bit

A version of Qwen/Qwen3.5-4B, tuned by FiditeNemini for local agent work and quantised to MLX 8-bit (affine, group size 64). It's a thinking model: answers start with reasoning in <think>โ€ฆ</think>.

It's the default model of MLX-Minions, a native macOS app that runs local agents on an in-process MLX model. MLX-Minions loads the text path only (via mlx-swift-lm), and the vision weights go unused.

Use

With mlx-lm or mlx-vlm on Apple silicon, as with any MLX Qwen3.5 checkpoint. MLX-Minions downloads a pinned revision and checks every file's SHA-256 before loading it.

Licence

Apache 2.0, the base model's licence.

Downloads last month
82
Safetensors
Model size
5B params
Tensor type
U32
ยท
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for FiditeNemini/Qwen3.5-4B-thinking-mlx-8bit

Finetuned
Qwen/Qwen3.5-4B
Finetuned
(1,484)
this model