Qwen 3 VL 8B Instruct
Qwen 3 VL 8B Instruct is a chat model developed by Qwen, capable of processing up to 262,144 tokens and handling various inputs including text and images. It excels in multimodal reasoning, particularly in STEM and math-related tasks, and features advanced spatial perception and visual recognition capabilities.
Input
Output
Context
262K
Max Output
33K
Parameters
8.8B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens32,768 tokens
Parameters8.8B
Release DateOct 11, 2025
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
2.9%
HLE
42.7%
GPQA
17.4%
SciCode
68.6%
MMLU Pro
27.3
Math
7.3
Coding
33.2%
LiveCodeBench
8.4
Intelligence
145
Speed (tok/s)
0.944
TTFA (s)
0.944
TTFT (s)
Resources & Links
Estimated GPU Requirements for Qwen 3 VL 8B Instruct
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.