Skip to content

ala-la

Qwen3.6-35B-A3B-pipeline-mixed34

ala-la/Qwen3.6-35B-A3B-pipeline-mixed34

Qwen3.6-35B-A3B-pipeline-mixed34 is a text generation model from ala-la. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.

Compressed Qwen3.6-35B-A3B-abliterated-v2 (uncensored MoE, 70.2 GB FP16) to 19.94 GB using a 4-stage pipeline: AWQ + QuaRot + mixed 3/4-bit quantization + bias compensation.

Downloads · 30 days

53

6% of all-time downloads

All-time downloads

911

Public

Parameters

9.1B

187 GB on disk

Likes

1

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors19.9 GB · 99%

Parameter types

How the weights are stored.

U83.8B · 42%

Try a prompt

Base models

Task
Text Generation
Library
transformers
Type
qwen3_5_moe
License
other
Languages
en, zh
Created
Jul 13, 2026
Updated
Jul 13, 2026