Aya 23 35B

Overview

Cohere For AI's 35B pre-Expanse multilingual model on the Command base, covering 23 languages with strong instruction following — but locked to non-commercial use.

When to pick this model

• Research baselines for multilingual instruction following
• Non-commercial multilingual chat in low-resource languages
• Comparisons against Aya Expanse 32B successor
• Academic evaluation across 23 languages

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	20 GB
Q5_K_M	25 GB
Q8_0	37 GB
FP16 (no quantization)	70 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

• Strong native quality across 23 languages
• Good instruction following in non-English settings
• Backed by Cohere's Command base architecture
• Competitive multilingual coverage for its era

Limitations

• CC-BY-NC 4.0 license blocks commercial deployment
• ~20 GB VRAM at Q4 with only 8k context
• Reasoning capabilities lag 2025-class open models

Architecture & training

Architecture: Dense · 35B · Cohere Command R+ backbone · 23 native languages

Training: Cohere For AI — 23 languages including FR/AR/ZH, multilingual instruction data.

Quick start

ollama run aya:35b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.