Qwen3.5 4B (MLX, 5-bit, text only)

Derived from a copy of mlx-community/Qwen3.5-4B-bf16 at revision 491fdc7c087ba7fb48adcb1253f8e76d011db783 (of Qwen/Qwen3.5-4B, revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a), by the Qwen team, Alibaba Cloud. This is not an official release.

Changes

Quantised to 5 bit with mlx-lm (text part only). No retraining.

Licence

Apache License 2.0, as the source — see LICENSE.

All rights to the model remain with its authors. SHA256SUMS, where present, lists the checksum of every file.

Downloads last month: 125

Safetensors

Model size

4B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Audante/Qwen3.5-4B-MLX-5bit

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(606)

this model