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

Libraries

How to use QuantFactory/Falcon3-10B-Instruct-GGUF with Transformers:

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

llama-cpp-python

How to use QuantFactory/Falcon3-10B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/Falcon3-10B-Instruct-GGUF",
	filename="Falcon3-10B-Instruct.Q2_K.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 QuantFactory/Falcon3-10B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

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 QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

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 QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantFactory/Falcon3-10B-Instruct-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/Falcon3-10B-Instruct-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 QuantFactory/Falcon3-10B-Instruct-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 QuantFactory/Falcon3-10B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use QuantFactory/Falcon3-10B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

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": "QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use QuantFactory/Falcon3-10B-Instruct-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 QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

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 QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use QuantFactory/Falcon3-10B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Falcon3-10B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Falcon3-10B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Falcon3-10B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/Falcon3-10B-Instruct-GGUF

This is quantized version of tiiuae/Falcon3-10B-Instruct created using llama.cpp

Original Model Card

Falcon3-10B-Instruct

Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.

This repository contains the Falcon3-10B-Instruct. It achieves state-of-the-art results (at the time of release) on reasoning, language understanding, instruction following, code and mathematics tasks. Falcon3-10B-Instruct supports 4 languages (English, French, Spanish, Portuguese) and a context length of up to 32K.

Model Details

Architecture
- Transformer-based causal decoder-only architecture
- 40 decoder blocks
- Grouped Query Attention (GQA) for faster inference: 12 query heads and 4 key-value heads
- Wider head dimension: 256
- High RoPE value to support long context understanding: 1000042
- Uses SwiGLu and RMSNorm
- 32K context length
- 131K vocab size
Depth up-scaled from Falcon3-7B-Base with 2 Teratokens of datasets comprising of web, code, STEM, high quality and mutlilingual data using 1024 H100 GPU chips
Posttrained on 1.2 million samples of STEM, conversational, code, safety and function call data
Supports EN, FR, ES, PT
Developed by Technology Innovation Institute
License: TII Falcon-LLM License 2.0
Model Release Date: December 2024

Getting started

Click to expand

from transformers import AutoTokenizer, AutoModelForCausalLM


from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "tiiuae/Falcon3-10B-Instruct"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many hours in one day?"
messages = [
    {"role": "system", "content": "You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Benchmarks

We report in the following table our internal pipeline benchmarks.

We use lm-evaluation harness.
We report raw scores obtained by applying chat template without fewshot_as_multiturn (unlike Llama3.1).
We use same batch-size across all models.

Category	Benchmark	Yi-1.5-9B-Chat	Mistral-Nemo-Base-2407 (12B)	Falcon3-10B-Instruct
General	MMLU (5-shot)	70	65.9	71.6
	MMLU-PRO (5-shot)	39.6	32.7	44
	IFEval	57.6	63.4	78
Math	GSM8K (5-shot)	76.6	73.8	83.1
	GSM8K (8-shot, COT)	78.5	73.6	81.3
	MATH Lvl-5 (4-shot)	8.8	0.4	22.1
Reasoning	Arc Challenge (25-shot)	51.9	61.6	64.5
	GPQA (0-shot)	35.4	33.2	33.5
	GPQA (0-shot, COT)	16	12.7	32.6
	MUSR (0-shot)	41.9	38.1	41.1
	BBH (3-shot)	49.2	43.6	58.4
CommonSense Understanding	PIQA (0-shot)	76.4	78.2	78.4
	SciQ (0-shot)	61.7	76.4	90.4
	Winogrande (0-shot)	-	-	71.3
	OpenbookQA (0-shot)	43.2	47.4	48.2
Instructions following	MT-Bench (avg)	8.28	8.6	8.17
Instructions following	Alpaca (WC)	25.81	45.44	24.7
Tool use	BFCL AST (avg)	48.4	74.2	86.3
Code	EvalPlus (0-shot) (avg)	69.4	58.9	74.7
Code	Multipl-E (0-shot) (avg)	-	34.5	45.8

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.

Technical Report

Coming soon....

Citation

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

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

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	35.19
IFEval (0-Shot)	78.17
BBH (3-Shot)	44.82
MATH Lvl 5 (4-Shot)	25.91
GPQA (0-shot)	10.51
MuSR (0-shot)	13.61
MMLU-PRO (5-shot)	38.10

Downloads last month: 171

GGUF

Model size

10B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Model tree for QuantFactory/Falcon3-10B-Instruct-GGUF

Base model

tiiuae/Falcon3-10B-Base

Quantized

(26)

this model

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

78.170
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

44.820
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

25.910
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

10.510
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

13.610
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

38.100