glm-4.6

glm-4.6

67.2K Downloads Updated 4 months ago

Advanced agentic, reasoning and coding capabilities.

tools thinking cloud

ollama run glm-4.6:cloud

curl http://localhost:11434/api/chat \
  -d '{
    "model": "glm-4.6:cloud",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='glm-4.6:cloud',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'glm-4.6:cloud',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model glm-4.6:cloud

Codex

Codex ollama launch codex --model glm-4.6:cloud

OpenCode

OpenCode ollama launch opencode --model glm-4.6:cloud

OpenClaw

OpenClaw ollama launch openclaw --model glm-4.6:cloud

Models

Name

1 model

Size

Context

Input

glm-4.6:cloud

198K context window · Text · 4 months ago

glm-4.6:cloud

-

198K

Text

Readme

Model Introduction

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、Cline、Roo 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.

<img src="/assets/library/glm-4.6/a2820004-9cb2-45ea-af09-7074224ddd49" width="120" />

## Model Introduction

**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、Cline、Roo 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**.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)