Skip to content

Qwen3.5 35B A3B

Qwen
Code Multilingual Thinking Tool Calls Vision

Qwen3.5 35B A3B is a Mixture-of-Experts model from Alibaba's Qwen team with 35 billion total parameters but only 3 billion active per token, routed across 256 experts for extreme efficiency. It is natively multimodal, processing text, images, and video, with built-in thinking capabilities for chain-of-thought reasoning. The model supports a 262K context window and covers over 200 languages. Released under the Apache 2.0 license, it delivers flagship-level performance at a fraction of the compute cost, quantizing efficiently for self-hosted deployment on consumer hardware.

Hardware Configuration

Optional — for precise deployment recommendations
Quantization Quality Size Fit
MXFP4_MOE Very high 20.11 GB
Q8_K_XL High 36.04 GB
Q6_K_XL High 28.22 GB
Q5_K_XL Medium 23.22 GB
Q4_K_M Medium 18.49 GB
Q4_K_XL Medium 19.17 GB
Q3_K_M Low 15.54 GB
Q3_K_XL Low 16.06 GB
Q2_K_XL Low 12.04 GB
Q4_K_L Low 18.82 GB
Q6_K_S Low 26.56 GB
Last updated: March 13, 2026