Alibaba (Qwen team) · 30.5B (3.3B active) parameters · Apache 2.0
What GPU do you need to run Qwen3 30B-A3B?Memory, cards and speed.
Qwen3 30B-A3B needs about 20 GB of GPU memory (VRAM) at its smallest (4-bit), so a 24 GB card such as an RTX 4090 runs it. The cheapest card on our list that fits, an RTX 3090, costs about $0.155 an hour. At its largest (16-bit) it needs about 62 GB.
GPU memory
Qwen3 30B-A3B, by version.
Includes about 1.5 GB for the program and a short conversation (about 4,000 tokens). Long conversations need more. Speeds are ceilings: real speeds are usually half to two-thirds of them. How we work it out
| Version | Memory needed | Card size | Cards that fit | From | Top speed |
|---|---|---|---|---|---|
| 4-bit | about 20 GB | 24 GB | RTX 4090, RTX 5090, RTX 3090, RTX 3090 Ti | $0.155/hr on an RTX 3090 | Faster than its size suggests |
| 8-bit | about 34 GB | None | More than any consumer card holds | — | Faster than its size suggests |
| 16-bit | about 62 GB | None | More than any consumer card holds | — | Faster than its size suggests |
A mixture-of-experts model: it needs memory for all 30.5B parameters but uses only about 3.3B for each word, so it answers much faster than a dense model of the same size.
Run it
Start Qwen3 30B-A3B in minutes.
On KernelMachine, Rent a Chat model with it: it loads into the chat app by itself once the rental is ready, straight from Ollama to the machine, and is in the app's model menu. On any machine with Ollama, one command downloads and runs it. Ollama on a rented GPU
$ ollama run qwen3:30b
# Model files: huggingface.co/Qwen/Qwen3-30B-A3B
Common questions
Questions, answered plainly.
How much VRAM does Qwen3 30B-A3B need?
4-bit: about 20 GB; 8-bit: about 34 GB; 16-bit: about 62 GB. That includes about 1.5 GB for the program and a short conversation; longer conversations need more.
Can an RTX 4090 run Qwen3 30B-A3B?
Yes. Qwen3 30B-A3B (4-bit) needs about 20 GB, which fits in the RTX 4090's 24 GB.
How fast does Qwen3 30B-A3B run?
Faster than its size suggests. It's a mixture-of-experts model, so it reads only about 3.3B of its 30.5B parameters for each word.
Can I run Qwen3 30B-A3B on KernelMachine?
Yes. Rent a Chat model with Qwen3 30B-A3B, on this page, starts the chat app on the cheapest card with 24 GB or more, and qwen3:30b loads into it by itself once it's ready. Already renting a Chat model? Pick Qwen3 30B-A3B on the rental's page, or download qwen3:30b from the chat app's model menu.
Other models
Compare with other chat models.
Preparing an invite-only beta
Get an email when access opens.
No launch date is set. We'll email you once when KernelMachine opens. Nothing else.