Qwen 3.5 397B-A17B — VRAM, Speed & Local Setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 16 lutego 2026

Model library → Qwen 3.5 → Qwen 3.5 397B-A17B

Alibaba's Feb 16, 2026 flagship MoE model — 397B total, ~17B active. Even at aggressive sub-Q4 quantization it needs ~125 GB (e.g. a 128GB Mac Studio at ~24 tok/s). Not realistically self-hostable on consumer hardware; Ollama only lists a cloud-hosted `:cloud` tag, not a local download. Best treated as a reference/'what frontier open weights look like' entry rather than a local recommendation.

Qwen 3.5 397B-A17B needs about 240 GB of VRAM at IQ2_M (sub-Q4) — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters	397 Billion (~17B active)
Context window	262,144
Architecture	Hybrid Gated DeltaNet + MoE
Provider	Alibaba Cloud
Licence	Apache 2.0
Specified at	IQ2_M (sub-Q4)
System RAM	256 GB
Record updated	2026-02-16

Licence

Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

Quant	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	130.5 GB	131.3 GB	—	Won't fit
Q3_K_M	169.2 GB	170.0 GB	—	Won't fit
Q4_K_M	239.7 GB	240.5 GB	—	Won't fit
Q5_K_M	281.4 GB	282.2 GB	—	Won't fit
Q6_K	325.5 GB	326.3 GB	—	Won't fit
Q8_0	421.8 GB	422.6 GB	—	Won't fit
F16	794.0 GB	794.8 GB	—	Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Qwen 3.5 397B-A17B VRAM calculator.

Buy This HardwareApple Mac Studio M3 Ultra — 512 GB VRAM · 60 W board power Deploy in the Cloud NowRunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs Qwen 3.5 397B-A17B is the Apple M3 Ultra (512 GB).

Ujawnienie afiliacyjne: Niektóre odnośniki na tej stronie to linki afiliacyjne — jeśli dokonasz zakupu za ich pośrednictwem, LLM Configurator może otrzymać prowizję bez dodatkowych kosztów dla Ciebie. Jako uczestnik programu Amazon Associates, LLM Configurator zarabia na kwalifikujących się zakupach.

Apple Mac Studio M3 Ultra

512 GB VRAM · 60 W board power

Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.

Sprawdź cenę na Amazon

How to Run Qwen 3.5 397B-A17B

Install Ollama, then run:

ollama run qwen3.5:397b-cloud

Weights on Hugging Face: Qwen/Qwen3.5-397B-A17B-Instruct.

Best for: frontier tasks, enterprise, research, cloud api.

Can I Run Qwen 3.5 397B-A17B on My GPU?

Other Qwen 3.5 Sizes

Qwen 3.5 0.8B — about 1 GB VRAM at Q4_K_M
Qwen 3.5 2B — about 2 GB VRAM at Q4_K_M
Qwen 3.5 4B — about 3 GB VRAM at Q4_K_M
Qwen 3.5 9B — about 6 GB VRAM at Q4_K_M
Qwen 3.5 27B — about 17 GB VRAM at Q4_K_M
Qwen 3.5 35B-A3B — about 22 GB VRAM at Q4_K_M
Qwen 3.5 122B-A10B — about 74 GB VRAM at Q4_K_M

Qwen 3.5 397B-A17B — Frequently Asked Questions

How much VRAM does Qwen 3.5 397B-A17B need?

About 240 GB at IQ2_M (sub-Q4) — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Qwen 3.5 397B-A17B run on an RTX 4090 (24 GB)?

No. Qwen 3.5 397B-A17B needs about 240 GB at IQ2_M (sub-Q4), more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.

How do I run Qwen 3.5 397B-A17B locally?

Install Ollama and run `ollama run qwen3.5:397b-cloud`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Qwen 3.5 come in?

Qwen 3.5 0.8B (1 GB), Qwen 3.5 2B (2 GB), Qwen 3.5 4B (3 GB), Qwen 3.5 9B (6 GB), Qwen 3.5 27B (17 GB), Qwen 3.5 35B-A3B (22 GB), Qwen 3.5 122B-A10B (74 GB), Qwen 3.5 397B-A17B (240 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Qwen 3.5 models | VRAM calculator | Check your own hardware