Qwen 3 0.6B Graviton
Qwen 3 0.6B on a Graviton instance in your AWS account. A small Apache 2.0 model for instruction following and tool calling. It does not need a GPU quota.
- Runs on c7g.medium, c7g.large, or m7g.large
- 32K context, with thinking mode and tool calling
- More than 100 languages
- HTTPS on port 443 with a per-instance API key. Ready in about 2 minutes
Quick start
No GPU quota on this listing
c7g.medium is a Graviton instance. It does not count against the EC2 quota for Running On-Demand G and VT instances.
- Subscribe on AWS Marketplace. The free trial covers the software fee; EC2 charges still apply.
- Launch on c7g.medium. In the security group, allow TCP 443 from the addresses that will call the API, and TCP 22 only if you need SSH.
- Wait about 2 minutes. In the EC2 console, open the instance, then Actions, Monitor and troubleshoot, Get system log. When the model is ready the log shows the endpoint, the API key, and example requests.
curl -k https://PUBLIC_IP/healthz - Send a request with the API key. The certificate is self-signed, so use -k or pin the fingerprint from the system log.
curl -k https://PUBLIC_IP/v1/chat/completions \ -H "Authorization: Bearer API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"qwen3:0.6b","messages":[{"role":"user","content":"Hello"}]}'
Instance types on this listing: c7g.medium, c7g.large, m7g.large. The model name in requests is qwen3:0.6b.