Skip to content

netw52623

Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-10bit-mlx

netw52623/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-10bit-mlx

Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-10bit-mlx is a text generation model from netw52623. Use it when you need the model to write or continue text. It is set up for mlx.

Quant of https://huggingface.co/nightmedia/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-BF16 which quantizes some layers to 8-bit and keeps a good portion in bf16, arriving at ~10 bpw "10 bit".

Downloads · 30 days

27

3% of all-time downloads

All-time downloads

783

Public

Parameters

34.7B

44.1 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors44.1 GB · 100%

Parameter types

How the weights are stored.

U3226.9B · 78%

Try a prompt

Task
Text Generation
Library
mlx
Type
qwen3_5_moe
Languages
en
Created
Jul 5, 2026
Updated
Jul 5, 2026