Llama 3.1

Llama 3.1#

Llama 3.1 is Meta’s series of instruction-tuned, auto-regressive dense transformers optimized for multilingual dialogue, instruction following, and tool usage.

FuriosaAI publishes pre-compiled builds of the Llama 3.1 models under the furiosa-ai organization on the Hugging Face Hub, each shipping a Furiosa Executable Bundle (FXB) for running it on FuriosaAI RNGD with Furiosa-LLM. The same upstream 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 newer 70B revision see Llama 3.3.

Variants#

Model

Quantization

RNGD cards

Notes

furiosa-ai/Llama-3.1-8B-Instruct

None (16-bit)

1

8B instruction-tuned

  • Architecture: Llama 3.1 (dense), LlamaForCausalLM

  • Input / Output: Text / Text

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

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-3.1-8B-Instruct

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)

Launch the server with tool calling#

To enable tool (function) calling, start the server with the llama3_json tool-call parser (the parser used by the Llama 3 series):

furiosa-llm serve furiosa-ai/Llama-3.1-8B-Instruct \
  --enable-auto-tool-choice \
  --tool-call-parser llama3_json

Query the server#

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-3.1-8B-Instruct",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
    }' \
    | python -m json.tool

Tool calling#

With the server launched using --enable-auto-tool-choice --tool-call-parser llama3_json, you can pass tools 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#