Qwen3-32B-FP8

This repository contains a pre-compiled build of Qwen/Qwen3-32B-FP8 for running it on FuriosaAI RNGD with Furiosa-LLM.

Overview

Qwen3-32B is the dense 32B model in the Qwen3 series, an auto-regressive transformer that supports both a thinking mode for complex reasoning and a non-thinking mode for general dialogue, along with strong instruction following, multilingual coverage, and tool usage. Its intended use is the same as the upstream Qwen/Qwen3-32B-FP8, and it is released under the Apache 2.0 License.

• Architecture: Qwen3 (dense)
• Input / Output: Text / Text
• Supported Inference Engine: Furiosa LLM
• Supported Hardware: FuriosaAI RNGD

Quantization

Weights are quantized to FP8 (static), following the upstream FP8 release, and activations use dynamic FP8 quantization at runtime (per-token / per-block). The KV cache stays in 16-bit precision.

Features

• Reasoning. Qwen3-32B is a hybrid reasoning model: thinking mode is on by default and can be toggled per request via enable_thinking. Launch the server with --reasoning-parser qwen3 to have the reasoning content returned in a separate field (see Basic Usage below).
• Tool calling. The model supports tool (function) calling through the hermes tool-call parser, the parser used by the Qwen3 series.

Parallelism Strategy

On RNGD, Qwen3-32B-FP8 runs with a tensor-parallel size of 32 PEs, which maps to four RNGD cards (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

Serve the model with the qwen3 reasoning parser so the chain of thought is returned in a separate field:

furiosa-llm serve furiosa-ai/Qwen3-32B-FP8 \
  --reasoning-parser qwen3

To also enable tool (function) calling, add the hermes tool-call parser (the parser used by the Qwen3 series):

furiosa-llm serve furiosa-ai/Qwen3-32B-FP8 \
  --reasoning-parser qwen3 \
  --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/Qwen3-32B-FP8",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
    }' \
    | python -m json.tool

With --reasoning-parser qwen3, the thinking content is returned separately from the final answer:

• response.choices[].message.reasoning (non-streaming)
• response.choices[].delta.reasoning (streaming)

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")

response = client.chat.completions.create(
    model="furiosa-ai/Qwen3-32B-FP8",
    messages=[{"role": "user", "content": "How many r's are in 'strawberry'?"}],
)

print("Reasoning:", response.choices[0].message.reasoning)
print("Answer:", response.choices[0].message.content)

Note: The reasoning field is not part of the OpenAI API specification but is a widely followed convention (the OpenAI Agents SDK, vLLM, and others). It appears only in responses that contain reasoning content; accessing it otherwise raises an AttributeError.

Advanced Usage

Toggling thinking. Qwen3-32B is a hybrid model: it reasons by default and can switch thinking on and off. To turn thinking off for a single request, pass enable_thinking through chat_template_kwargs; the response then carries no reasoning content, so read only message.content:

# Disable thinking for a single request
response = client.chat.completions.create(
    model="furiosa-ai/Qwen3-32B-FP8",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print(response.choices[0].message.content)

To default every request to non-thinking, launch the server with --default-chat-template-kwargs (a request can still re-enable thinking with its own chat_template_kwargs):

furiosa-llm serve furiosa-ai/Qwen3-32B-FP8 \
  --reasoning-parser qwen3 \
  --default-chat-template-kwargs '{"enable_thinking": false}'

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/Qwen3-32B-FP8 — upstream model card