Skip to content

Aya Expanse 32B

CC-BY-NC-4.0

Cohere · 32B · transformer-decoder

🤗 HuggingFace Ollama Official
2025-10-15 8K context 32B params

Use Cases

chat multilingual writing summary

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_Mrec422.0 GBGood—
Q8_0838.0 GBExcellent—

About this model

Aya Expanse 32B is Cohere's flagship multilingual model, covering 23 languages with higher quality than its 8B sibling. It delivers strong multilingual generation, translation, and comprehension. At Q4 it needs about 22 GB VRAM, fitting on a RTX 3090/4090 or a Mac with 24 GB+ unified memory. The best open multilingual model for users who work across multiple languages.