Qwen 3 30B-A3B (MoE) — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated April 28, 2025

Model library → Qwen 3 → Qwen 3 30B-A3B (MoE)

Qwen 3's efficient MoE model — 30B total parameters but only 3B active per token. Delivers 14B-quality responses at 7B inference speed. The best efficiency-to-quality ratio in the Qwen 3 family.

Qwen 3 30B-A3B (MoE) needs about 19 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.

Specifications

Parameters30 Billion (3B active)
Context window128,000
ArchitectureMoE
ProviderAlibaba Cloud
LicenceApache 2.0
Specified atQ4_K_M
System RAM16 GB
Record updated2025-04-28

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), at 8K context. 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.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K10.0 GB11.6 GB~237 tok/s (est.)Fits comfortably
Q3_K_M13.0 GB14.6 GB~216 tok/s (est.)Fits comfortably
Q4_K_M18.4 GB20.0 GB~185 tok/s (est.)Fits comfortably
Q5_K_M21.6 GB23.2 GB~170 tok/s (est.)Tight fit
Q6_K25.0 GB26.6 GB~24 tok/s (est.)Offloads to system RAM (slow)
Q8_032.4 GB34.0 GB~20 tok/s (est.)Offloads to system RAM (slow)
F1661.0 GB62.6 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Qwen 3 30B-A3B (MoE) VRAM calculator.

Buy This HardwareAMD Radeon RX 7900 XT 20GB — 20 GB VRAM · 315 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

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 30B-A3B (MoE) is the AMD Radeon RX 7900 XT (20 GB).

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.
AMD Radeon RX 7900 XT 20GB
20 GB VRAM · 315 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run Qwen 3 30B-A3B (MoE)

Install Ollama, then run:

ollama run qwen3:30b-a3b

Weights on Hugging Face: Qwen/Qwen3-30B-A3B.

Best for: fast reasoning, chat, coding, efficient.

Can I Run Qwen 3 30B-A3B (MoE) on My GPU?

Other Qwen 3 Sizes

Qwen 3 30B-A3B (MoE) — Frequently Asked Questions

How much VRAM does Qwen 3 30B-A3B (MoE) need?
About 19 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 30B-A3B (MoE) run on an RTX 4090 (24 GB)?
Yes. Qwen 3 30B-A3B (MoE) needs about 19 GB at Q4_K_M, inside a 24 GB card, at an estimated 185 tokens/sec.
How do I run Qwen 3 30B-A3B (MoE) locally?
Install Ollama and run `ollama run qwen3:30b-a3b`. 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.

← All Qwen 3 models | VRAM calculator | Build a PC for this model | Check your own hardware