Qwen2.5-0.5B-Instruct

This repository contains a pre-compiled build of Qwen/Qwen2.5-0.5B-Instruct for running it on FuriosaAI RNGD with Furiosa-LLM.

Overview

Qwen2.5-0.5B-Instruct is the smallest instruction-tuned model in the Qwen2.5 series, an auto-regressive dense transformer with about 0.5B parameters. Despite its size it offers solid instruction following, multilingual coverage, and tool usage, making it well suited to lightweight and latency-sensitive deployments. Its intended use is the same as the upstream Qwen/Qwen2.5-0.5B-Instruct, and it is released under the Apache 2.0 License.

• Architecture: Qwen2 (dense)
• Input / Output: Text / Text
• Supported Inference Engine: Furiosa LLM
• Supported Hardware: FuriosaAI RNGD

Quantization

No quantization — the model runs in its native 16-bit precision.

Features

• Tool calling. The model supports tool (function) calling through the hermes tool-call parser, the parser used by the Qwen series.

Parallelism Strategy

On RNGD, Qwen2.5-0.5B-Instruct runs with a tensor-parallel size of 4 PEs, which fits on a single RNGD card (8 PEs per card).

Usage

To run this model with Furiosa-LLM, follow the example commands below after installing Furiosa-LLM and its prerequisites.

Launch the server

The simplest way to serve the model is:

# Launch the server, listening on port 8000 by default
furiosa-llm serve furiosa-ai/Qwen2.5-0.5B-Instruct

To also enable tool (function) calling, add the hermes tool-call parser (the parser used by the Qwen series):

furiosa-llm serve furiosa-ai/Qwen2.5-0.5B-Instruct \
  --enable-auto-tool-choice \
  --tool-call-parser hermes

When the server is ready, you will see:

INFO:     Started server process [27507]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

Basic Usage

The server exposes an OpenAI-compatible API. You can send a request with curl:

curl http://localhost:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
    "model": "furiosa-ai/Qwen2.5-0.5B-Instruct",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
    }' \
    | python -m json.tool

Advanced Usage

Tool calling. With the server launched using --enable-auto-tool-choice --tool-call-parser hermes (see Launch the server), pass tools in the request and let the model decide when to call them. See the Tool Calling guide for a complete client example and details on tool-choice options.

Learn more

• Tool Calling — parsers, tool-choice options, and more examples
• Furiosa-LLM Server (furiosa-llm serve) — full OpenAI-compatible API reference and serving options
• Qwen/Qwen2.5-0.5B-Instruct — upstream model card