Qwen3.5-0.8B

Name: Qwen3.5-0.8B
Author: Alibaba

Multimodal

Alibaba

Qwen3.5-0.8B is a 0.8 billion parameter vision-language model using Gated DeltaNet hybrid architecture with a 3:1 ratio of linear attention to full softmax attention. It supports 262K native context length and features both thinking and non-thinking modes.

Key Specifications

Parameters

800.0M

Context

Release Date

March 2, 2026

Average Score

31.6%

API Documentation Repository Model Weights

Timeline

Key dates in the model's history

Announcement

March 2, 2026

Last Update

September 12, 2026

Today

October 5, 2026

Technical Specifications

Parameters

800.0M

Training Tokens

Knowledge Cutoff

Family

Capabilities

MultimodalZeroEval

Benchmark Results

Model performance metrics across various tests and benchmarks

Reasoning

Logical reasoning and analysis

GPQA

Thinking mode • Self-reported

11.9%

Other Tests

Specialized benchmarks

AA-LCR

Thinking mode • Self-reported

4.7%

BFCL-V4

Thinking mode • Self-reported

25.3%

C-Eval

Thinking mode • Self-reported

50.5%

Global PIQA

Thinking mode • Self-reported

59.4%

IFBench

Thinking mode • Self-reported

21.0%

IFEval

Thinking mode • Self-reported

44.0%

Include

Thinking mode • Self-reported

40.6%

LongBench v2

Thinking mode • Self-reported

26.1%

MAXIFE

Thinking mode • Self-reported

39.2%

MMLU-Pro

Thinking mode • Self-reported

42.3%

MMLU-ProX

Thinking mode • Self-reported

34.6%

MMLU-Redux

Thinking mode • Self-reported

59.5%

MMMLU

Thinking mode • Self-reported

44.3%

Multi-Challenge

Thinking mode • Self-reported

18.9%

NOVA-63

Thinking mode • Self-reported

42.4%

PolyMATH

Thinking mode • Self-reported

8.2%

SuperGPQA

Thinking mode • Self-reported

21.3%

t2-bench

Thinking mode • Self-reported

11.6%

WMT24++

Thinking mode • Self-reported

27.2%

License & Metadata

License

apache_2_0

Announcement Date

March 2, 2026

Last Updated

September 12, 2026

Similar Models

All Models

Qwen2.5 VL 7B Instruct

Alibaba

MM8.3B

Released:Jan 2025

Alibaba

MM2.0B

Best score:0.5 (GPQA)

Released:Mar 2026

QvQ-72B-Preview

Alibaba

MM73.4B

Released:Dec 2024

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.