GLM 4.5V FP8
GLM 4.5V is a vision-language chat model from Z.ai, based on the GLM-4.5-Air text foundation model. It is genuinely best at handling diverse visual content for tasks like image reasoning, video understanding, document analysis, and GUI agent operations.
Input
Output
Context
66K
Max Output
16K
Parameters
107.8B
Technical Specifications
Model TypeChat
Context Window65,536 tokens
Max Output Tokens16,384 tokens
Parameters107.8B
Release DateAug 10, 2025
Training CutoffDec 1, 2024
Licensemit
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
5.9%
HLE
68.4%
GPQA
22.5%
Tau2-Bench
73.0%
AIME 2025
34.2%
IFBench
22.1%
SciCode
78.8%
MMLU Pro
73.0
Math
60.4%
LiveCodeBench
9.1
Intelligence
5.3%
Terminal-Bench Hard
Estimated GPU Requirements for GLM 4.5V FP8
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 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.