Text vLLM (OpenAI-compatible API)

Qwen3 32B (AWQ)

The flagship dense Qwen3, 4-bit AWQ quantised to run on a single RTX 5090.

Overview

Qwen3 32B is the largest dense model in the Qwen3 family. The official AWQ 4-bit weights (~19 GB) let it run on one 32 GB GPU with a 12K context — the most capable general model you can serve on a single card.

Key features

✓
Strongest dense Qwen3
✓
Official 4-bit AWQ weights
✓
12K context on this template

Use cases

→
High-quality private chat
→
Complex document analysis
→
Evaluation baseline for fine-tunes

On this template

Runs on the vLLM (OpenAI-compatible API) template, exposing its OpenAI-compatible API at a private HTTPS address. You also get root SSH and JupyterLab.

`MODEL_ID`	`Qwen/Qwen3-32B-AWQ`
`VLLM_ARGS`	`--max-model-len 12288 --gpu-memory-utilization 0.93`

Quick start

Click Deploy and pick an available GPU — only offers with enough VRAM are shown.
Wait for the status to turn running. The first start downloads the model, which can take a few minutes.
Use the connection details on your rental page:

curl

curl https://r12-abcd1234-app.gpu.clearlayer.ca/v1/chat/completions \
  -H "Authorization: Bearer <app-token>" \
  -H "Content-Type: application/json" \
  -d '{"model": "Qwen/Qwen3-32B-AWQ", "messages": [{"role": "user", "content": "Hello!"}]}'

Python

from openai import OpenAI

client = OpenAI(base_url="https://r12-abcd1234-app.gpu.clearlayer.ca/v1", api_key="<app-token>")
resp = client.chat.completions.create(
    model="Qwen/Qwen3-32B-AWQ",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)