Local LLM model page

CodeGeeX4 (9B)

Versatile code completion model from THUDM. Multi-language coding. 187K downloads.

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

Can CodeGeeX4 (9B) run locally?

CodeGeeX4 (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: codegeex4-all-9b

Hugging Face repository: THUDM/codegeex4-all-9b-GGUF

codestandard

Strengths

  • Versatile code completion model from THUDM. Multi-language coding. 187K downloads.

Limitations

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

Best use cases

  • code
  • standard

Benchmarks

Speed: 7/10

Quality: 6/10

Coding: 8/10

Reasoning: 6/10

Technical details

Developer: codegeex

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-07