No official torrent yet β requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from furiosa-ai/Qwen3-30B-A3B-FP8
All models by furiosa-ai βThis repository contains Qwen/Qwen3-30B-A3B-FP8 together with a Furiosa Executable Bundle (FXB) for running it on FuriosaAI RNGD with Furiosa-LLM. The same model also runs on other frameworks (such as vLLM, SGLang, and Transformers); for usage with those, see the upstream Qwen/Qwen3-30B-A3B-FP8 model card.
Qwen3-30B-A3B is an auto-regressive Mixture-of-Experts (MoE) transformer with 30.5B total parameters of which about 3.3B are activated per token. It is a hybrid reasoning model that supports both thinking and non-thinking modes within a single model β switchable per request β and offers strong reasoning over text, instruction following, multilingual coverage, and tool usage. Its intended use is the same as the upstream Qwen/Qwen3-30B-A3B-FP8, and it is released under the Apache 2.0 License.
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.
enable_thinking. Launch the server with --reasoning-parser qwen3 to have Furiosa-LLM parse the chain of thought into a separate field (see Basic Usage below).hermes tool-call parser, the parser used by the Qwen3 series.On RNGD, Qwen3-30B-A3B-FP8 runs with a tensor-parallel size of 32 PEs, which maps to four RNGD cards (8 PEs per card).
To run this model with Furiosa-LLM, follow the example commands below after installing Furiosa-LLM and its prerequisites.
Qwen3-30B-A3B-FP8 is a hybrid model that reasons by default and can switch
thinking on and off (see Advanced Usage). Serve it with the
qwen3 reasoning parser so the chain of thought is returned in a separate field:
To also enable tool (function) calling, add the hermes tool-call parser (the
parser used by the Qwen3 series):
When the server is ready, you will see:
The server exposes an OpenAI-compatible API. You can send a request with curl:
In thinking mode, Qwen3-30B-A3B-FP8 returns its reasoning separately from the
final answer:
response.choices[].message.reasoning (non-streaming)response.choices[].delta.reasoning (streaming)Note: The
reasoningfield 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 anAttributeError.
Toggling thinking. Qwen3-30B-A3B-FP8 reasons by default. 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:
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):
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.
furiosa-llm serve) β full OpenAI-compatible API reference and serving optionsfuriosa-llm serve furiosa-ai/Qwen3-30B-A3B-FP8 \ --reasoning-parser qwen3furiosa-llm serve furiosa-ai/Qwen3-30B-A3B-FP8 \ --reasoning-parser qwen3 \ --enable-auto-tool-choice \ --tool-call-parser hermesINFO: 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)curl http://localhost:8000/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "furiosa-ai/Qwen3-30B-A3B-FP8", "messages": [{"role": "user", "content": "What is the capital of France?"}] }' \ | python -m json.toolfrom openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create( model="furiosa-ai/Qwen3-30B-A3B-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)# Disable thinking for a single requestresponse = client.chat.completions.create( model="furiosa-ai/Qwen3-30B-A3B-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)furiosa-llm serve furiosa-ai/Qwen3-30B-A3B-FP8 \ --reasoning-parser qwen3 \ --default-chat-template-kwargs '{"enable_thinking": false}'