Qwen 3.5 35B A3B
Qwen develops the Qwen 3.5 35B A 3B FP 8 model, a chat model capable of handling text and image inputs, with strengths in areas like reasoning and visual understanding, as evidenced by its top 25% GPQA score. It features a context window of 262,144 tokens and utilizes an efficient hybrid architecture combining Gated Delta Networks with sparse Mixture-of-Experts.
Input
Output
Context
262K
Max Output
82K
Parameters
36B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens81,920 tokens
Parameters36B
Release DateFeb 24, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
19.7%
HLE
84.5%
GPQA
37.7%
SciCode
30.3
Coding
29.3
Intelligence
160
Speed (tok/s)
13.6
TTFA (s)
1.1
TTFT (s)
Resources & Links
Estimated GPU Requirements for Qwen 3.5 35B A3B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.