Instructions to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF", dtype="auto")

llama-cpp-python

How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF",
	filename="ggml-model-i2_s.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF
# Run inference directly in the terminal:
llama-cli -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF
# Run inference directly in the terminal:
llama-cli -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF
# Run inference directly in the terminal:
./llama-cli -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Use Docker

docker model run hf.co/tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

LM Studio
Jan
Ollama
How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with Ollama:
```
ollama run hf.co/tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF
```

Unsloth Studio new

How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF to start chatting

Pi new

How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Run Hermes

hermes

Docker Model Runner
How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF
```

Lemonade

How to use tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Run and chat with the model

lemonade run user.Falcon3-10B-Instruct-1.58bit-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

TL;DR
Model Details
Training Details
Usage
Evaluation
Citation

TL;DR

Model Details

Model Description

Developed by: https://www.tii.ae
Model type: Causal decoder-only - instruct / chat version
Architecture: Pure-transformer - 1.58bit version
Language(s) (NLP): Mainly English
License: TII Falcon License 2.0

Training details

The model has been trained following the training strategies from the recent 1-bit LLM HF blogpost and 1-bit LLM paper. For more details about the training protocol of this model, please refer to the Falcon-3 technical report, section Compression.

Usage

Currently to use this model you can rely on BitNet library. You can also play with the model using the falcon-1.58bit playground (only for the 7B instruct version).

BitNet

git clone https://github.com/microsoft/BitNet && cd BitNet
pip install -r requirements.txt
huggingface-cli download tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF ggml-model-i2_s.gguf --local-dir models/Falcon3-10B-1.58bit/
python run_inference.py -m models/Falcon3-10B-1.58bit/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv

Evaluation

We report in the following table our internal pipeline benchmarks:

Note evaluation results are normalized score from v2 leaderboard tasks - reported results of original models in the blogpost are raw scores

Benchmark	Llama3-8B-1.58-100B-tokens	Falcon3-10B-Instruct-1.58bit
IFEval	17.91	54.37
MUSR	4.87	2.57
GPQA	1.83	4.27
BBH	5.36	6.59
MMLU-PRO	2.78	6.62
MATH	0.26	2.44
Average	5.5	12.81

Useful links

View our release blogpost.
Feel free to join our discord server if you have any questions or to interact with our researchers and developers.

Citation

If the Falcon3 family of models were helpful to your work, feel free to give us a cite.

@misc{Falcon3,
    title = {The Falcon 3 Family of Open Models},
    author = {Falcon-LLM Team},
    month = {December},
    year = {2024}
}

Downloads last month: 297

GGUF

Model size

10B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tiiuae/Falcon3-10B-Instruct-1.58bit-GGUF

Base model

tiiuae/Falcon3-10B-Base

Finetuned

tiiuae/Falcon3-10B-Instruct

Quantized

(41)

this model

tiiuae
/

Falcon3-10B-Instruct-1.58bit-GGUF

Table of Contents