GLM-4.6-FP8

馃憢 Join our Discord community.
馃摉 Check out the GLM-4.6 technical blog, technical report(GLM-4.5), and Zhipu AI technical documentation.
馃搷 Use GLM-4.6 API services on Z.ai API Platform.
馃憠 One click to GLM-4.6.

Model Introduction

Compared with GLM-4.5, GLM-4.6 brings several key improvements:

  • Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.
  • Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code銆丆line銆丷oo Code and Kilo Code, including improvements in generating visually polished front-end pages.
  • Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.
  • More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.
  • Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.

We evaluated GLM-4.6 across eight public benchmarks covering agents, reasoning, and coding. Results show clear gains over GLM-4.5, with GLM-4.6 also holding competitive advantages over leading domestic and international models such as DeepSeek-V3.1-Terminus and Claude Sonnet 4.

bench

Inference

Both GLM-4.5 and GLM-4.6 use the same inference method.

you can check our github for more detail.

Recommended Evaluation Parameters

For general evaluations, we recommend using a sampling temperature of 1.0.

For code-related evaluation tasks (such as LCB), it is further recommended to set:

  • top_p = 0.95
  • top_k = 40

Evaluation

  • For tool-integrated reasoning, please refer to this doc.
  • For search benchmark, we design a specific format for searching toolcall in thinking mode to support search agent, please refer to this. for the detailed template.
Downloads last month
6
Safetensors
Model size
357B params
Tensor type
F32
BF16
I8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support