MODEL FAMILY

Qwen3.5

Choose the size and format you want to run. Compare each version’s hardware fit, model scores, and setup guides in one place.

AgentsTextCodingImages

3versions to explore

5published guides

Compare versions

PERSONALIZE THE COMPARISONWhich machine will you use?

Save your hardware to compare which versions can run on your machine.

Add my hardware

FIND YOUR VERSION

Compare versions

Scores and requirements stay with each version.

4B languageAgents

Qwen3.5 · 4B

A compact vision-language model for reasoning, coding, agents, and image understanding.

Model size: 4B language
Format: Ollama 4B package
Context: 262,144 native

Freshness 41 out of 100. Repository age: 230 days old, Feb 27, 2026. Measures age, not quality.

Popularity 91 out of 100. 7,944,995 downloads in 30 days; 1,073 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

SETUP GUIDES FOR THIS VERSIONChat locally with Qwen3.5 · 4B Analyze images locally with Qwen3.5 Qwen3.5 · 9B private chat setup See all 4 guides

Explore this version Model source

9BText

Qwen3.5 · 9B

An open-weight vision-language model with a compact Ollama package suitable for a private assistant or coding help.

Model size: 9B
Format: Ollama 9B package
Context: 262,144 native

Freshness 41 out of 100. Release age: 230 days old, Feb 27, 2026. Measures age, not quality.

Popularity 93 out of 100. 8,591,266 downloads in 30 days; 2,171 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

SETUP GUIDES FOR THIS VERSIONAsk your documents locally with Qwen3.5 · 9B Qwen3.5 · 9B private chat setup

Explore this version Model source

35B total · 3B activeCoding

Qwen3.5-35B-A3B is an Apache-2.0 licensed causal language model with a vision encoder, hosted in the Qwen/Qwen3.5-35B-A3B repository. It supports image-text-to-text generation and is provided in Hugging Face Transformers format with safetensors weights. The model has 35B total parameters with 3B activated, uses a hybrid architecture combining Gated DeltaNet, Gated Attention, and a sparse Mixture-of-Experts layer, and supports a native context length of 262,144 tokens, extensible up to 1,010,000 tokens. It is based on Qwen/Qwen3.5-35B-A3B-Base and is described as compatible with Hugging Face Transformers, vLLM, SGLang, and KTransformers. The model card highlights a unified vision-language foundation, efficient hybrid architecture, scalable reinforcement learning, coverage of 201 languages and dialects, and a next-generation training infrastructure.

Model size: 35B total · 3B active
Format: Ollama 35B A3B package
Context: 262,144 native

Freshness 41 out of 100. Repository age: 233 days old, Feb 24, 2026. Measures age, not quality.

Popularity 83 out of 100. 1,484,223 downloads in 30 days; 1,534 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

Arena Open Source Web coding: rank 51 of 55. Ranked model: qwen3.5-35b-a3b. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+1

Explore this version Model source

Compare versions

Qwen3.5 · 4B

Qwen3.5 · 9B

Qwen3.5 · 35B A3B