Local LLM model page

GLM-4 (32B)

Flagship GLM-4. Much better than QwQ 32B for general tasks. Llama-70B class performance at half the size. Exceptional bilingual (CN/EN).

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
32B
Minimum RAM
32 GB
Model size
20 GB
Quantization
Q4_K_M

Can GLM-4 (32B) run locally?

GLM-4 (32B) is best suited for power-user machines with 32 GB RAM. LocalClaw recommends Q4_K_M as the default quantization, with at least 32 GB RAM.

Search term for LM Studio or compatible runtimes: glm-4-32b-chat

Hugging Face repository: THUDM/glm-4-32b-chat-GGUF

chatcodepowerqualitygeneral

Strengths

  • Flagship GLM-4. Much better than QwQ 32B for general tasks. Llama-70B class performance at half the size. Exceptional bilingual (CN/EN).

Limitations

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

Best use cases

  • chat
  • code
  • power
  • quality
  • general

Benchmarks

Speed: 4/10

Quality: 9/10

Coding: 9/10

Reasoning: 9/10

Technical details

Developer: glm

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-08