Text vLLM (OpenAI-compatible API)

Qwen3 14B (FP8)

Larger Qwen3 in official FP8 weights — noticeably stronger reasoning while fitting comfortably on one GPU.

Overview

The 14B member of the Qwen3 family, served from Qwen's official FP8 checkpoint. Blackwell GPUs run FP8 natively, so you get near-BF16 quality at roughly half the memory.

Key features

✓
Official FP8 checkpoint
✓
Thinking / non-thinking modes
✓
Tool calling

Use cases

→
Agents that need better reasoning
→
RAG over company documents
→
Data extraction pipelines

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/Qwen3-14B-FP8`
`VLLM_ARGS`	`--max-model-len 16384 --gpu-memory-utilization 0.92`

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/Qwen3-14B-FP8", "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/Qwen3-14B-FP8",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)