Qwen3 Coder 30B A3B VRAM requirements
Qwen · 30.5B params (3.3B active) · Apache 2.0. Estimates, not vendor numbers.
Qwen3 Coder 30B A3B (30.5B parameters, 3.3B active per token) needs about 20 GB of VRAM or unified memory at Q4, 23 GB at Q5 and 34 GB at Q8 (weights plus about 1.5 GB headroom, our estimate). The smallest common setup that runs it is 24GB GPU (RTX 4090).
| Quant | Download | Memory needed |
|---|---|---|
| Q4 | 18 GB | 20 GB |
| Q5 | 22 GB | 23 GB |
| Q8 | 32 GB | 34 GB |
Will it run on my machine?
| Setup | Runs? | Speed est. |
|---|---|---|
| 8GB GPU (RTX 4060) | No | n/a |
| 12GB GPU (RTX 3060 / 4070) | No | n/a |
| 16GB GPU (RTX 4060 Ti 16GB) | No | n/a |
| 24GB GPU (RTX 4090) | Yes, Q4 | ~305 tok/s |
| 32GB GPU (RTX 5090) | Yes, Q5 | ~457 tok/s |
| Mac 16GB (M4) | No | n/a |
| Mac 48GB (M4 Pro) | Yes, Q8 | ~47 tok/s |
| Mac 128GB (M4 Max) | Yes, Q8 | ~93 tok/s |
| PC, 32GB RAM, no GPU | No | n/a |
Best quant that fits each setup, with estimated generation speed from memory bandwidth. Real speed depends on the runtime, context length and settings.
Mixture of experts: 30.5B total, 3.3B active per token, so it runs fast for its size.
FAQ
How much VRAM does Qwen3 Coder 30B A3B need?
About 20 GB at Q4, 23 GB at Q5 and 34 GB at Q8, including about 1.5 GB headroom. These are estimates from the parameter count on the official model card.
Can Qwen3 Coder 30B A3B run on 8GB of VRAM?
Not fully on the GPU. At Q4 it needs about 20 GB; partial CPU offload works but is much slower.
Can Qwen3 Coder 30B A3B run on a Mac?
Yes. Mac 48GB (M4 Pro), Mac 128GB (M4 Max) can run it.
Which quant of Qwen3 Coder 30B A3B should I use?
Use the highest quant that fits with room to spare: Q8 is near full quality, Q5 is a good balance, and Q4 is the smallest that usually keeps quality acceptable.
Why is Qwen3 Coder 30B A3B fast for its size?
It is a mixture of experts: 30.5B parameters in total but only 3.3B are used per token, so it reads less memory per token. You still need memory for all 30.5B.
Similar-size models
Qwen3.6 27B (27B) · Qwen3.8 27B (27.8B) · Muse Glimmer 30B (29.6B) · Gemma 4 31B (30.7B) · DeepSeek R1 Distill Qwen 32B (32.8B) · Qwen3.6 35B A3B (35B)