gpuos

Fast MoE · Pro plan

Run Qwen3 30B A3B on your own GPU

A mixture-of-experts model with 30B parameters but only 3B active per token, so it answers several times faster than a dense 32B model while keeping most of its quality.

With gpuos, Qwen3 30B A3B runs on Ollama at Q4_K_M on your machine and is served as qwen3-30b-a3b through one OpenAI-compatible endpoint, with API keys, quotas and usage metering.

Parameters
30B MoE (3B active)
Quantization
Q4_K_M
VRAM (4–8K ctx)
≈ 20 GB
Context window
32K tokens
License
Apache 2.0
Engine
Ollama
Ollama tag
qwen3:30b-a3b
API
/v1/chat/completions

What Qwen3 30B A3B is good at

Which GPUs can run Qwen3 30B A3B?

Catalog estimate at Q4_K_M, not a measured benchmark. Chat estimates assume a short context; embedding memory depends on input and batch size. More in how much VRAM an LLM needs.

Check this estimate against your GPU with the VRAM calculator

Call Qwen3 30B A3B with the OpenAI SDK

Same SDKs, same request format. Only the base URL, the key and the model name change. Setup for LangChain, Continue, Open WebUI and more is in integrations.

Python
from openai import OpenAI

client = OpenAI(base_url="https://gpuos.si/v1", api_key="gpuos_key_…")
stream = client.chat.completions.create(
    model="qwen3-30b-a3b",
    messages=[{"role": "user", "content": "Summarize our refund policy."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")
Node.js
import OpenAI from "openai"

const client = new OpenAI({ baseURL: "https://gpuos.si/v1", apiKey: process.env.GPUOS_API_KEY })
const reply = await client.chat.completions.create({
  model: "qwen3-30b-a3b",
  messages: [{ role: "user", content: "Summarize our refund policy." }],
})
console.log(reply.choices[0].message.content)
curl
curl https://gpuos.si/v1/chat/completions \
  -H "Authorization: Bearer $GPUOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3-30b-a3b", "messages": [{"role": "user", "content": "Hello"}]}'

Questions

How much VRAM does Qwen3 30B A3B need?
About 20 GB at Q4_K_M with a short context (4–8K tokens). The smallest common GPU that fits it is the RTX 3090 / 4090 24 GB. Longer contexts and more concurrent requests need extra headroom for the KV cache.
Can I use Qwen3 30B A3B commercially?
Yes. Qwen3 30B A3B is released under the Apache 2.0 license, which allows commercial use.
Is Qwen3 30B A3B compatible with the OpenAI API?
Yes. Through gpuos, Qwen3 30B A3B is served at /v1/chat/completions with the model id "qwen3-30b-a3b", so the official OpenAI SDKs, LangChain and LlamaIndex work by changing the base URL and the API key.
Which gpuos plan includes Qwen3 30B A3B?
Qwen3 30B A3B is part of the full catalog on the Pro plan, $29 per GPU per month.

Related models

Plan your Qwen3 30B A3B deployment with gpuOS

Join early access for onboarding, or read the quickstart to evaluate the Community workflow on your own GPU.

Join early accessRead the quickstart