Local LLM model page

CodeGemma (7B)

Google code completion model. Excellent for inline code suggestions. 1.2M downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
7B
Minimum RAM
8 GB
Model size
4.5 GB
Quantization
Q5_K_M

Can CodeGemma (7B) run locally?

CodeGemma (7B) 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: codegemma-7b-it

Hugging Face repository: lmstudio-community/codegemma-7b-it-GGUF

codestandard

Strengths

  • Google code completion model. Excellent for inline code suggestions. 1.2M downloads.

Limitations

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

Best use cases

  • code
  • standard

Benchmarks

Speed: 8/10

Quality: 6/10

Coding: 8/10

Reasoning: 5/10

Technical details

Developer: gemma

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-04