Qwen3-Coder 30B-A3B (MoE) — VRAM, Speed & Local Setup

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

Written by Jakub Rusinowski · Last updated September 19, 2026

Model library → Qwen3-Coder → Qwen3-Coder 30B-A3B (MoE)

The most-run local coding model. 30.5B total with 3.3B active per token, so it streams like a 3B while reasoning like a 30B, and a 24 GB card holds it comfortably at Q4. 48 layers, 128 experts with 8 active, and a native 262,144-token context.

Qwen3-Coder 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

Parameters	30.5 Billion (3.3B active)
Context window	262,144
Architecture	MoE
Provider	Alibaba Cloud
Licence	Apache 2.0
Specified at	Q4_K_M
System RAM	32 GB
Record updated	2026-09-19

Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed.

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). Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. 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	Bits/weight	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	2.63	10 GB	11.6 GB	~237 tok/s (est.)	Fits comfortably
Q3_K_M	3.41	13 GB	14.6 GB	~216 tok/s (est.)	Fits comfortably
Q4_K_M	4.83	18.4 GB	20 GB	~185 tok/s (est.)	Fits comfortably
Q5_K_M	5.67	21.6 GB	23.2 GB	~170 tok/s (est.)	Tight fit
Q6_K	6.56	25 GB	26.6 GB	~24 tok/s (est.)	Offloads to system RAM (slow)
Q8_0	8.50	32.4 GB	34 GB	~20 tok/s (est.)	Offloads to system RAM (slow)
F16	16.00	61 GB	62.6 GB	—	Won't fit

Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.

Buy This HardwareAMD Radeon RX 7900 XT 20GB — 20 GB VRAM · 315 W board power Deploy 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 Qwen3-Coder 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 Qwen3-Coder 30B-A3B (MoE)

Install Ollama, then run:

ollama run qwen3-coder:30b

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

Best for: coding, agents, repo tasks, local assistant.

Can I Run Qwen3-Coder 30B-A3B (MoE) on My GPU?

Other Qwen3-Coder Sizes

Qwen3-Coder 80B-A3B (MoE) — about 49 GB VRAM at Q4_K_M
Qwen3-Coder 480B-A35B (MoE) — about 291 GB VRAM at Q4_K_M

Qwen3-Coder 30B-A3B (MoE) — Frequently Asked Questions

How much VRAM does Qwen3-Coder 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 Qwen3-Coder 30B-A3B (MoE) run on an RTX 4090 (24 GB)?

Yes. Qwen3-Coder 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 Qwen3-Coder 30B-A3B (MoE) locally?

Install Ollama and run `ollama run qwen3-coder:30b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Qwen3-Coder come in?

Qwen3-Coder 8B (6 GB), Qwen3-Coder 30B-A3B (MoE) (19 GB), Qwen3-Coder 80B-A3B (MoE) (49 GB), Qwen3-Coder 480B-A35B (MoE) (291 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Qwen3-Coder models | VRAM calculator | Check your own hardware