Qwen3.5 9B

Name: Qwen3.5 9B
Author: Alibaba

Alibaba

Qwen3.5 9B is a compact model from the Qwen3.5 series with reasoning capabilities. Suitable for local deployment while maintaining a high level of intelligence.

Key Specifications

Parameters

9.0B

Context

Release Date

March 1, 2026

Average Score

86.7%

API Documentation Repository Model Weights Results Blog

Timeline

Key dates in the model's history

Announcement

March 1, 2026

Last Update

March 21, 2026

Today

September 5, 2026

Technical Specifications

Parameters

9.0B

Training Tokens

Knowledge Cutoff

Family

Capabilities

MultimodalZeroEval

Benchmark Results

Model performance metrics across various tests and benchmarks

Other Tests

Specialized benchmarks

IFEval

Mode thinking • Self-reported

92.0%

MMLU-Redux

Mode thinking • Self-reported

91.0%

C-Eval

Mode thinking • Self-reported

88.0%

MAXIFE

Mode thinking • Self-reported

83.0%

Global PIQA

Mode thinking • Self-reported

83.0%

HMMT 2025

2025 • Self-reported

83.0%

License & Metadata

License

apache-2.0

Announcement Date

March 1, 2026

Last Updated

March 21, 2026

Articles about Qwen3.5 9B

TurboQuant Now Runs Qwen 3.5-9B on a MacBook Air

A developer used Google's TurboQuant compression in llama.cpp to run Qwen 3.5-9B with 20K context on a base MacBook Air M4 with just 16GB of RAM.

March 30, 2026

3 min

Similar Models

All Models

Qwen2.5 7B Instruct

Alibaba

7.6B

Best score:0.8 (HumanEval)

Released:Sep 2024

Price:$0.30/1M tokens

Qwen2 7B Instruct

Alibaba

7.6B

Best score:0.8 (HumanEval)

Released:Jul 2024

Qwen2.5-Coder 7B Instruct

Alibaba

7.0B

Best score:0.9 (HumanEval)

Released:Sep 2024

Qwen3 Max

Alibaba

Best score:0.6 (GPQA)

Released:Dec 2025

Qwen3.7 Max

Alibaba

Released:May 2026

Price:$2.50/1M tokens

Qwen3-Next-80B-A3B-Instruct

Alibaba

80.0B

Released:Sep 2025

Price:$0.15/1M tokens

Qwen2 72B Instruct

Alibaba

72.0B

Best score:0.9 (HumanEval)

Released:Jul 2024

Qwen3 30B A3B

Alibaba

30.5B

Best score:0.7 (GPQA)

Released:Apr 2025

Price:$0.10/1M tokens

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.