GLM 5.3 Flash
GLM 5.3 Flash is a large-scale, natively multimodal chat model developed by Z.ai. It employs a hybrid architecture combining sparse and linear attention and has a context window of 1,048,576 tokens.
Input
Output
Context
1049K
Max Output
48K
Parameters
321.3B
Technical Specifications
Model TypeChat
Context Window1,048,576 tokens
Max Output Tokens48,000 tokens
Parameters321.3B
Release DateAug 25, 2026
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
39.9%
HLE
78.0%
AA-LCR
91.2%
GPQA
46.1%
SciCode
47.2%
Tau2 Banking
71.5
Coding
57.5
Intelligence
84.3%
Terminal-Bench 2.1
49.2
Speed (tok/s)
41.9
TTFA (s)
1.2
TTFT (s)
Estimated GPU Requirements for GLM 5.3 Flash
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Z.ai
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 28, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.