Local LLM model page

Granite 4 (8B)

IBM latest instruction + tool-use model. Best Granite yet. 20K downloads.

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

Can Granite 4 (8B) run locally?

Granite 4 (8B) 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: granite-4-8b-instruct

Hugging Face repository: ibm-granite/granite-4-8b-instruct-GGUF

chatstandardgeneral

Strengths

  • IBM latest instruction + tool-use model. Best Granite yet. 20K downloads.

Limitations

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

Best use cases

  • chat
  • standard
  • general

Benchmarks

Speed: 8/10

Quality: 7/10

Coding: 7/10

Reasoning: 7/10

Technical details

Developer: granite

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-07