Qwen 3.5 397B-A17B

Overview

Alibaba's flagship MoE with 397B total and 17B active parameters, ranked #5 open-weight on Artificial Analysis. Apache 2.0 with a 262K context.

When to pick this model

• Top-tier open-weight performance on a multi-GPU server
• Long-context enterprise workloads
• Replacing closed frontier models with self-hosted weights
• Commercial deployments needing Apache licensing

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	240 GB
Q5_K_M	285 GB
Q8_0	425 GB
FP16 (no quantization)	794 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

• #5 on Artificial Analysis's open leaderboard
• 262K context window
• Only 17B active parameters keeps inference efficient
• Apache 2.0 license

Limitations

• 240GB+ in Q4 demands a multi-GPU server
• MoE deployment adds operational complexity
• Beaten by GLM-5.1 and MiniMax-M2.7 on key benchmarks

Architecture & training

Architecture: MoE 397B/17B active · 262k ctx · hybrid thinking

Training: New flagship of the Qwen 3.5 family.

Quick start

# HuggingFace : Qwen/Qwen3.5-397B-A17B (alternative locale plus accessible : ollama run qwen3.5:122b)

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