Alibaba Cloud397B (17B active)~240 GB VRAM at IQ2_M (sub-Q4)

Qwen 3.5 397B-A17B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

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.

Logic96
Creative94
Coding95

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
131.3 GB—Too big
Q3_K_M
3.41 bpw
170 GB—Too big
Q4_K_M
4.83 bpw
240.5 GB—Too big
Q5_K_M
5.67 bpw
282.2 GB—Too big
Q6_K
6.56 bpw
326.3 GB—Too big
Q8_0
8.50 bpw
422.6 GB—Too big
F16
16.00 bpw
794.8 GB—Too big

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Qwen 3.5 397B-A17B VRAM calculator →

Get Qwen 3.5 397B-A17B running

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

Buy this hardware Apple Mac Studio M3 Ultra — 512 GB VRAM · 60 W board powerDeploy in the cloud now RunPod

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.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Apple Mac Studio M3 Ultra
512 GB VRAM · 60 W board power
2026 prices are volatile — check the current listing.

How to run Qwen 3.5 397B-A17B

The Ollama tag `qwen3.5:397b-cloud` is cloud-hosted, so there is no local run command for this model.

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

Specifications

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Parameters
397 Billion (~17B active)
Context window
262,144
Architecture
Hybrid Gated DeltaNet + MoE
Provider
Alibaba Cloud
Licence
Apache 2.0
Practical deployment
Workstation (large unified memory or pro GPU)
Specified at
IQ2_M (sub-Q4)
System RAM
256 GB
Record updated
2026-02-16
LicenceApache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forfrontier tasksenterpriseresearchcloud api

Can I run Qwen 3.5 397B-A17B on my GPU?

Other Qwen 3.5 sizes

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?

The Ollama tag `qwen3.5:397b-cloud` is cloud-hosted, so there is no local run command for this model. Running the published tag would send your prompts to a hosted GPU rather than your own 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.