GLM 4.6V FP8
GLM-4.6V is a 106B parameter multimodal chat model from Z.ai, designed for cloud and high-performance cluster scenarios. It is genuinely best at visual understanding and native multimodal function calling, enabling vision-driven tool use directly from images without text conversion.
Input
Output
Context
131K
Max Output
33K
Parameters
107.8B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens32,768 tokens
Parameters107.8B
Release DateDec 7, 2025
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
8.9%
HLE
40.3%
AA-LCR
71.9%
GPQA
31.6%
Tau2-Bench
85.3%
AIME 2025
30.1%
IFBench
30.4%
SciCode
79.9%
MMLU Pro
85.3
Math
16.0%
LiveCodeBench
16.8
Intelligence
14.4%
Terminal-Bench Hard
Estimated GPU Requirements for GLM 4.6V 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 8, 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.