Local LLM model page

Aya Expanse (32B)

Cohere's multilingual powerhouse — 23 languages including Arabic, Hindi, Japanese, Polish. State-of-the-art on multilingual benchmarks at 32B scale. CC-BY-NC 4.0.

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

Can Aya Expanse (32B) run locally?

Aya Expanse (32B) is best suited for power-user machines with 32 GB RAM. LocalClaw recommends Q4_K_M as the default quantization, with at least 24 GB RAM.

Search term for LM Studio or compatible runtimes: aya-expanse-32b

Hugging Face repository: CohereLabs/aya-expanse-32b-GGUF

chatmultilingualpowerquality

Strengths

  • Cohere's multilingual powerhouse — 23 languages including Arabic, Hindi, Japanese, Polish. State-of-the-art on multilingual benchmarks at 32B scale. CC-BY-NC 4.0.

Limitations

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

Best use cases

  • chat
  • multilingual
  • power
  • quality

Benchmarks

Speed: 4/10

Quality: 8/10

Coding: 7/10

Reasoning: 8/10

Technical details

Developer: cohere

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-10