Zai
GLM 5.2 FP8
GLM-5.2 is Z.ai's flagship chat model designed for long-horizon tasks, featuring a stable 1,048,576-token context window. It demonstrates top-tier performance in coding benchmarks and advanced reasoning tasks.
Input
Output
Context
1049K
Max Output
131K
Parameters
753.4B
Technical Specifications
Model TypeChat
Context Window1,048,576 tokens
Max Output Tokens131,072 tokens
Parameters753.4B
Release DateJun 16, 2026
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
40.1%
HLE
71.3%
AA-LCR
89.5%
GPQA
99.1%
Tau2-Bench
73.3%
IFBench
50.5%
SciCode
26.8%
Tau2 Banking
68.8
Coding
51.1
Intelligence
50.8%
Terminal-Bench Hard
77.9%
Terminal-Bench 2.1
158
Speed (tok/s)
13.7
TTFA (s)
1.1
TTFT (s)
Estimated GPU Requirements for GLM 5.2 FP8
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Zai
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 6, 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.