Qwen 3 0.6B FP8
Qwen builds Qwen 3 0.6B FP 8, a chat model that excels at reasoning, instruction-following, and multilingual support, with capabilities including function calling, JSON mode, and text generation. Its architecture features a context window of 40,960 tokens and a mixture-of-experts (MoE) design, allowing for seamless switching between thinking and non-thinking modes.
Input
Output
Context
41K
Max Output
-
Parameters
751.7M
Technical Specifications
Model TypeChat
Context Window40,960 tokens
Max Output TokensNot available
Parameters751.7M
Release DateApr 28, 2025
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
5.7%
HLE
10.0%
AIME
23.9%
GPQA
2.8%
SciCode
75.0%
MATH 500
34.7%
MMLU Pro
18.0
Math
0.900
Coding
12.1%
LiveCodeBench
1.3
Intelligence
Resources & Links
Estimated GPU Requirements for Qwen 3 0.6B FP8
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.