Instructions to use second-state/Falcon3-3B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/Falcon3-3B-Instruct-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="second-state/Falcon3-3B-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("second-state/Falcon3-3B-Instruct-GGUF")
model = AutoModelForCausalLM.from_pretrained("second-state/Falcon3-3B-Instruct-GGUF")

llama-cpp-python

How to use second-state/Falcon3-3B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/Falcon3-3B-Instruct-GGUF",
	filename="Falcon3-3B-Instruct-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use second-state/Falcon3-3B-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 second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/Falcon3-3B-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 second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/Falcon3-3B-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 second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/Falcon3-3B-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 second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/Falcon3-3B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/Falcon3-3B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Falcon3-3B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M

SGLang

How to use second-state/Falcon3-3B-Instruct-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "second-state/Falcon3-3B-Instruct-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Falcon3-3B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "second-state/Falcon3-3B-Instruct-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Falcon3-3B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use second-state/Falcon3-3B-Instruct-GGUF with Ollama:
```
ollama run hf.co/second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use second-state/Falcon3-3B-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 second-state/Falcon3-3B-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 second-state/Falcon3-3B-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 second-state/Falcon3-3B-Instruct-GGUF to start chatting

Pi new

How to use second-state/Falcon3-3B-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 second-state/Falcon3-3B-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": "second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use second-state/Falcon3-3B-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 second-state/Falcon3-3B-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 second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use second-state/Falcon3-3B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use second-state/Falcon3-3B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/Falcon3-3B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Falcon3-3B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Falcon3-3B-Instruct-GGUF

Original Model

tiiuae/Falcon3-3B-Instruct

Run with LlamaEdge

LlamaEdge version: v0.16.0 and above

Prompt template

Prompt type: falcon3

Prompt string

<|system|>
You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible.
<|user|>
{user_message}
<|assistant|>

Context size: 32000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-3B-Instruct-Q5_K_M.gguf \
  llama-api-server.wasm \
  --model-name Falcon3-3B-Instruct \
  --prompt-template falcon3 \
  --ctx-size 32000

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-3B-Instruct-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template falcon3 \
  --ctx-size 32000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Falcon3-3B-Instruct-Q2_K.gguf	Q2_K	2	1.35 GB	smallest, significant quality loss - not recommended for most purposes
Falcon3-3B-Instruct-Q3_K_L.gguf	Q3_K_L	3	1.78 GB	small, substantial quality loss
Falcon3-3B-Instruct-Q3_K_M.gguf	Q3_K_M	3	1.67 GB	very small, high quality loss
Falcon3-3B-Instruct-Q3_K_S.gguf	Q3_K_S	3	1.55 GB	very small, high quality loss
Falcon3-3B-Instruct-Q4_0.gguf	Q4_0	4	1.92 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Falcon3-3B-Instruct-Q4_K_M.gguf	Q4_K_M	4	2.01 GB	medium, balanced quality - recommended
Falcon3-3B-Instruct-Q4_K_S.gguf	Q4_K_S	4	1.93 GB	small, greater quality loss
Falcon3-3B-Instruct-Q5_0.gguf	Q5_0	5	2.28 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Falcon3-3B-Instruct-Q5_K_M.gguf	Q5_K_M	5	2.32 GB	large, very low quality loss - recommended
Falcon3-3B-Instruct-Q5_K_S.gguf	Q5_K_S	5	2.28 GB	large, low quality loss - recommended
Falcon3-3B-Instruct-Q6_K.gguf	Q6_K	6	2.65 GB	very large, extremely low quality loss
Falcon3-3B-Instruct-Q8_0.gguf	Q8_0	8	3.43 GB	very large, extremely low quality loss - not recommended
Falcon3-3B-Instruct-f16.gguf	f16	16	6.46 GB

Quantized with llama.cpp b4381

Downloads last month: 118

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for second-state/Falcon3-3B-Instruct-GGUF

Unable to build the model tree, the base model loops to the model itself. Learn more.

Collection including second-state/Falcon3-3B-Instruct-GGUF

Falcon3-Instruct GGUF Models

Collection

LlamaEdge compatible quants for Falcon3-Instruct models. • 4 items • Updated Dec 23, 2024