DeepSeek R1 Distill Qwen 7B

Small reasoning model distilled from DeepSeek-R1 — shows its chain of thought, strong at maths.

Overview

Distilled from DeepSeek-R1's reasoning traces into a Qwen2.5 7B base. It writes out its reasoning before the answer, which makes it good at maths and step-by-step problems for its size.

Key features

• ✓
  Explicit chain-of-thought
• ✓
  Long 32K context for long reasoning
• ✓
  MIT licence

Use cases

• →
  Maths and logic tutoring
• →
  Reasoning experiments
• →
  Cheap reasoning backend

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	deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
VLLM_ARGS	--max-model-len 32768 --gpu-memory-utilization 0.90

Quick start

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

curl https://r12-abcd1234-app.gpu.clearlayer.ca/v1/chat/completions \
  -H "Authorization: Bearer <app-token>" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "messages": [{"role": "user", "content": "Hello!"}]}'

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="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)