Qwen 3 30B-A3B (MoE) — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
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.
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.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 11.6 GB | ~237 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 14.6 GB | ~216 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 20 GB | ~185 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 23.2 GB | ~170 tok/s | Tight | |
| Q6_K 6.56 bpw | 26.6 GB | ~24 tok/s | Offload | |
| Q8_0 8.50 bpw | 34 GB | ~20 tok/s | Offload | |
| F16 16.00 bpw | 62.6 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 30B-A3B (MoE) VRAM calculator →
Get Qwen 3 30B-A3B (MoE) running
The cheapest catalogued GPU that runs Qwen 3 30B-A3B (MoE) is the AMD Radeon RX 7900 XTX (24 GB).
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.
How to run Qwen 3 30B-A3B (MoE)
Install Ollama, then run:
ollama run qwen3:30b-a3bSpecifications
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
- 30 Billion (3B active)
- Context window
- 128,000
- Architecture
- MoE
- Provider
- Alibaba Cloud
- Licence
- Apache 2.0
- Practical deployment
- Single consumer GPU
- Specified at
- Q4_K_M
- System RAM
- 16 GB
- Record updated
- 2025-04-28
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.
Can I run Qwen 3 30B-A3B (MoE) on my GPU?
- Qwen 3 30B-A3B (MoE) on AMD Radeon RX 7800 XT
- Qwen 3 30B-A3B (MoE) on AMD Radeon RX 7900 XT
- Qwen 3 30B-A3B (MoE) on AMD Radeon RX 7900 XTX
- Qwen 3 30B-A3B (MoE) on AMD Radeon RX 9060 XT 16GB
- Qwen 3 30B-A3B (MoE) on AMD Radeon RX 9060 XT 8GB
- Qwen 3 30B-A3B (MoE) on AMD Radeon RX 9070
- Qwen 3 30B-A3B (MoE) on AMD Radeon RX 9070 XT
- Qwen 3 30B-A3B (MoE) on Apple M1
- Qwen 3 30B-A3B (MoE) on Apple M1 Pro
- Qwen 3 30B-A3B (MoE) on Apple M2 Pro
- Qwen 3 30B-A3B (MoE) on Apple M2 Ultra
- Qwen 3 30B-A3B (MoE) on Apple M3 Pro
- Qwen 3 30B-A3B (MoE) on Apple M4
- Qwen 3 30B-A3B (MoE) on Apple M5
- Qwen 3 30B-A3B (MoE) on Intel Arc B570
- Qwen 3 30B-A3B (MoE) on Intel Arc B580
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 3060 (12GB)
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 3070
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 3070 Ti
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 3080 (10GB)
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 3090
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4060
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4060 Ti 16GB
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4070
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4070 Super
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4070 Ti
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4070 Ti Super
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4080
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4080 Super
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 4090
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 5060
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 5060 Ti 16GB
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 5060 Ti 8GB
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 5070
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 5070 Ti
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 5080
- Qwen 3 30B-A3B (MoE) on NVIDIA GeForce RTX 5090
- Qwen 3 30B-A3B (MoE) on NVIDIA L40S
- Qwen 3 30B-A3B (MoE) on NVIDIA RTX 6000 Ada Generation
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.