Llama 3.3

Llama 3.3#

Llama 3.3 is Meta’s instruction-tuned, auto-regressive dense transformer optimized for multilingual dialogue, instruction following, and tool usage, with quality competitive with much larger models.

Furiosa-LLM runs Llama 3.3 in FP8 using the RedHatAI FP8-dynamic recipe (static FP8 weights with dynamic FP8 activation quantization). FuriosaAI publishes a pre-compiled build under the furiosa-ai organization on the Hugging Face Hub, shipping a Furiosa Executable Bundle (FXB) for running it on FuriosaAI RNGD with Furiosa-LLM. The same weights also run on other frameworks (such as vLLM, SGLang, and Transformers); for usage with those, see the upstream model card linked below.

For the smaller 8B model see Llama 3.1.

Available Models#

Model

Quantization

RNGD cards

Notes

furiosa-ai/Llama-3.3-70B-Instruct-FP8-dynamic

FP8 (dynamic)

4

70B instruction-tuned

  • Architecture: Llama 3.3 (dense), LlamaForCausalLM

  • Input / Output: Text / Text

  • Quantization: The linear (Transformer block) weights are quantized to FP8 (static), and activations use dynamic FP8 quantization at runtime (per-token, without offline calibration).

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/Llama-3.3-70B-Instruct-FP8-dynamic

To also enable tool (function) calling, add the llama3_json tool-call parser (the parser used by the Llama 3 series):

furiosa-llm serve furiosa-ai/Llama-3.3-70B-Instruct-FP8-dynamic \
  --enable-auto-tool-choice \
  --tool-call-parser llama3_json

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/Llama-3.3-70B-Instruct-FP8-dynamic",
    "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 llama3_json (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#