Qwen 3.5 397B-A17B
By Alibaba · China
Updated 2026-07-13
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.
In practice, Qwen 3.5 397B-A17B is server-class even at Q4_K_M (240 GB). Stepping up to Q8_0 nearly doubles the footprint to 425 GB, and unquantized FP16 weights take 794 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Qwen 3.5 397B-A17B needs roughly 280 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 2 tokens/sec on entry-level GPUs, on the order of 7 tokens/sec on a mid-range card, and up to 20 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Qwen 3.5 397B-A17B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Qwen 3.5 397B-A17B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 240 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 240 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Does not fit — needs 240 GB at Q4_K_M |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Does not fit — needs 240 GB at Q4_K_M |
| 32 GB | RTX 5090 | Does not fit — needs 240 GB at Q4_K_M |
Which GPU should you buy to run Qwen 3.5 397B-A17B?
To run Qwen 3.5 397B-A17B locally at Q4, you need ~240 GB of VRAM. The best value for this is a Apple Mac Studio (64+ GB unified memory).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
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
Typical workloads
In our catalog grid, Qwen 3.5 397B-A17B is filed under Open Frontier, Reasoning, Multilingual — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multi-step reasoning and math-flavoured tasks; multilingual workloads.
The 255k-token context window is large enough to hold entire codebases' worth of files or long reports in a single prompt, which is what makes local RAG and document analysis practical. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.
Architecture & training
Architecture: MoE 397B/17B active · 262k ctx · hybrid thinking
Training: New flagship of the Qwen 3.5 family.
A strong flagship MoE with permissive licensing, though no longer the top of the open leaderboard.
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.
Similar models worth comparing
Frequently asked questions
How much VRAM does Qwen 3.5 397B-A17B need?
At the recommended Q4_K_M quantization, Qwen 3.5 397B-A17B needs about 240 GB of VRAM. Q8_0 takes 425 GB, and unquantized FP16 weights take 794 GB.
Can Qwen 3.5 397B-A17B run without a GPU?
Yes — with roughly 280 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Qwen 3.5 397B-A17B support?
Qwen 3.5 397B-A17B supports a 255k-token context window (262,000 tokens).
Can I use Qwen 3.5 397B-A17B commercially?
Yes. Qwen 3.5 397B-A17B is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Qwen 3.5 397B-A17B on consumer hardware?
Our compatibility engine estimates on the order of 7 tokens/sec on a mid-range GPU and up to 20 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Qwen 3.5 397B-A17B should I download first?
Start with Q4_K_M (240 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It does not fit a single 24 GB consumer card — plan for multi-GPU or server hardware.