Qwen 3 8B AWQ
Qwen develops the Qwen 3 8B, a chat model that excels at reasoning, instruction-following, and multilingual support, with a notable ability to seamlessly switch between thinking and non-thinking modes within a single model. Its context window of 40,960 tokens allows for complex and nuanced conversations.
Input
Output
Context
41K
Max Output
8K
Parameters
8.2B
Technical Specifications
Model TypeChat
Context Window40,960 tokens
Max Output Tokens8,192 tokens
Parameters8.2B
Release DateMay 3, 2025
Training CutoffMar 31, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.2%
HLE
74.7%
AIME
58.9%
GPQA
22.6%
SciCode
90.4%
MATH 500
74.3%
MMLU Pro
19.0
Math
9.0
Coding
40.6%
LiveCodeBench
7.4
Intelligence
63.2
Speed (tok/s)
33.0
TTFA (s)
1.4
TTFT (s)
Resources & Links
Estimated GPU Requirements for Qwen 3 8B AWQ
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 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.