Alibaba Cloud235B (22B active)~143 GB VRAM at Q4_K_M

Qwen 3 235B-A22B (MoE) — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

The flagship Qwen 3 model. 235B total with only 22B active per token — comparable compute cost to a dense 22B model. Tops open-source leaderboards. Requires Apple Silicon 128GB+ or multi-GPU.

Qwen 3 235B-A22B (MoE) needs about 143 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic99
Creative92
Coding99

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
79.6 GB—Too big
Q3_K_M
3.41 bpw
102.5 GB—Too big
Q4_K_M
4.83 bpw
144.3 GB—Too big
Q5_K_M
5.67 bpw
168.9 GB—Too big
Q6_K
6.56 bpw
195.1 GB—Too big
Q8_0
8.50 bpw
252.1 GB—Too big
F16
16.00 bpw
472.4 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 235B-A22B (MoE) VRAM calculator →

Get Qwen 3 235B-A22B (MoE) running

The cheapest catalogued GPU that runs Qwen 3 235B-A22B (MoE) 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 235B-A22B (MoE)

Install Ollama, then run:

ollama run qwen3:235b-a22b
Weights on Hugging Face: Qwen/Qwen3-235B-A22B ↗

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
235 Billion (22B active)
Context window
128,000
Architecture
MoE
Provider
Alibaba Cloud
Licence
Apache 2.0
Practical deployment
Workstation (large unified memory or pro GPU)
Specified at
Q4_K_M
System RAM
128 GB
Record updated
2025-04-28
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 reasoningcomplex codingresearchenterprise

Can I run Qwen 3 235B-A22B (MoE) on my GPU?

Other Qwen 3 sizes

Qwen 3 235B-A22B (MoE) — frequently asked questions

How much VRAM does Qwen 3 235B-A22B (MoE) need?

About 143 GB at Q4_K_M — 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 235B-A22B (MoE) run on an RTX 4090 (24 GB)?

No. Qwen 3 235B-A22B (MoE) needs about 143 GB at Q4_K_M, 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 235B-A22B (MoE) locally?

Install Ollama and run `ollama run qwen3:235b-a22b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Qwen 3 come in?

Qwen 3 8B (6 GB), Qwen 3 14B (10 GB), Qwen 3 32B (21 GB), Qwen 3 30B-A3B (MoE) (19 GB), Qwen 3 235B-A22B (MoE) (143 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.