Qwen 3 8B
Qwen 3 8B on a GPU instance in your AWS account. CPU sizes are listed for evaluation when you do not have GPU quota. Thinking mode and tool calling, billed by the hour.
- 32K context, with a longer window using YaRN
- Thinking mode and a direct-response mode
- More than 100 languages
- HTTPS on port 443 with a per-instance API key. Ready in about 4 minutes
Quick start
Check your GPU quota before you subscribe
GPU instances need the EC2 quota Running On-Demand G and VT instances (code L-DB2E81BA) in your Region. It must be at least the vCPU count of the instance (g4dn.xlarge has 4 vCPUs). New AWS accounts often start at 0, and the launch then fails. Check or request the quota.
- Subscribe on AWS Marketplace. The free trial covers the software fee; EC2 charges still apply.
- Launch on g4dn.xlarge. 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 4 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":"qwen3:8b","messages":[{"role":"user","content":"Hello"}]}'
Instance types on this listing: g4dn.xlarge, g4dn.2xlarge, g5.xlarge, g6.xlarge, g6e.xlarge, c7i.2xlarge, c7i.4xlarge, m7i.2xlarge. The model name in requests is qwen3:8b.