Skip to content

manjunathshiva

Qwen3.6-35B-A3B-tq3a-tqTe-g64

manjunathshiva/Qwen3.6-35B-A3B-tq3a-tqTe-g64

Qwen3.6-35B-A3B-tq3a-tqTe-g64 is a text generation model from manjunathshiva. 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.

Ternary (1.58-bit) expert TurboQuant quantization of Qwen/Qwen3.6-35B-A3B — 3-bit attention, ternary {-c, 0, +c} experts packed as base-3 trits (group size 64) — produced with TurboQuant-MLX.

Downloads · 30 days

295

9% of all-time downloads

All-time downloads

3.4K

Public

Parameters

2.9B

9.4 GB on disk

Likes

5

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors9.4 GB · 100%

Parameter types

How the weights are stored.

U321.8B · 63%

Try a prompt

Base models

Task
Text Generation
Library
mlx
Type
qwen3_5_moe
License
apache-2.0
Created
Jul 3, 2026
Updated
Oct 21, 2026