Local LLM model page

GLM-4 (9B)

Zhipu AI's efficient all-rounder. Strong bilingual performance (CN/EN). Model License (research/personal use; commercial contact Zhipu).

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
9B
Minimum RAM
8 GB
Model size
6 GB
Quantization
Q5_K_M

Can GLM-4 (9B) run locally?

GLM-4 (9B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 8 GB RAM.

Search term for LM Studio or compatible runtimes: glm-4-9b-chat

Hugging Face repository: THUDM/glm-4-9b-chat-GGUF

chatcodestandardgeneral

Strengths

  • Zhipu AI's efficient all-rounder. Strong bilingual performance (CN/EN). Model License (research/personal use; commercial contact Zhipu).

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • chat
  • code
  • standard
  • general

Benchmarks

Speed: 8/10

Quality: 7/10

Coding: 7/10

Reasoning: 7/10

Technical details

Developer: glm

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-06