NemoClaw Knowledge Wiki

Home

❯

entities

❯

glm 47 flash

glm-47-flash

Jun 14, 20261 min read

  • glm-model
  • mixture-of-experts
  • local-execution
  • ollama-integration
  • anthropic-api-compatibility

GLM-4.7-Flash

Architecture

  • Model Type: mixture-of-experts (MoE).
  • Parameters: 30B total parameters with 3B active parameters.

Local Deployment & Integration

  • Local Execution: Can be used to run claude-code locally.
  • Compatibility: Leverages ollama’s Anthropic API compatibility layer to interface with tools designed for Claude.

References

  • 2026 04 14 Ollama Claude GLM Channel Sam Witteveen

Source Notes

  • 2026-04-07: OpenClaw Autonomous AI Agent Setup Configuration and Advanced · ▶ source

Graph View

  • GLM-4.7-Flash
  • Architecture
  • Local Deployment & Integration
  • References
  • Source Notes

Backlinks

  • INDEX
  • anthropic-api-compatibility
  • api-emulation
  • coding-assistant
  • local-coding-assistants
  • local-llm-execution
  • nvidia-h100-gpus
  • ollama-launch-command
  • OpenClaw: Autonomous AI Agent Setup, Configuration, and Advanced Integration
  • OpenClaw: Autonomous AI Agent Setup, Configuration, and Advanced Integration
  • OpenClaw Autonomous AI Agent Setup Configuration and Advanced

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community