Instructions to use RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-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 RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-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 RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M
```
Unsloth Desktop

How to use RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M

Run and chat with the model

lemonade run user.TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-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 RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RichardErkhov/TheBlueObserver_-_Falcon3-3B-Instruct-MLX-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Falcon3-3B-Instruct-MLX - GGUF

Model creator: https://huggingface.co/TheBlueObserver/
Original model: https://huggingface.co/TheBlueObserver/Falcon3-3B-Instruct-MLX/

Name	Quant method	Size
Falcon3-3B-Instruct-MLX.Q2_K.gguf	Q2_K	1.26GB
Falcon3-3B-Instruct-MLX.IQ3_XS.gguf	IQ3_XS	1.39GB
Falcon3-3B-Instruct-MLX.IQ3_S.gguf	IQ3_S	1.44GB
Falcon3-3B-Instruct-MLX.Q3_K_S.gguf	Q3_K_S	1.44GB
Falcon3-3B-Instruct-MLX.IQ3_M.gguf	IQ3_M	1.48GB
Falcon3-3B-Instruct-MLX.Q3_K.gguf	Q3_K	1.56GB
Falcon3-3B-Instruct-MLX.Q3_K_M.gguf	Q3_K_M	1.56GB
Falcon3-3B-Instruct-MLX.Q3_K_L.gguf	Q3_K_L	1.66GB
Falcon3-3B-Instruct-MLX.IQ4_XS.gguf	IQ4_XS	1.72GB
Falcon3-3B-Instruct-MLX.Q4_0.gguf	Q4_0	1.79GB
Falcon3-3B-Instruct-MLX.IQ4_NL.gguf	IQ4_NL	1.8GB
Falcon3-3B-Instruct-MLX.Q4_K_S.gguf	Q4_K_S	1.8GB
Falcon3-3B-Instruct-MLX.Q4_K.gguf	Q4_K	1.87GB
Falcon3-3B-Instruct-MLX.Q4_K_M.gguf	Q4_K_M	1.87GB
Falcon3-3B-Instruct-MLX.Q4_1.gguf	Q4_1	1.96GB
Falcon3-3B-Instruct-MLX.Q5_0.gguf	Q5_0	2.12GB
Falcon3-3B-Instruct-MLX.Q5_K_S.gguf	Q5_K_S	2.12GB
Falcon3-3B-Instruct-MLX.Q5_K.gguf	Q5_K	2.16GB
Falcon3-3B-Instruct-MLX.Q5_K_M.gguf	Q5_K_M	2.16GB
Falcon3-3B-Instruct-MLX.Q5_1.gguf	Q5_1	2.29GB
Falcon3-3B-Instruct-MLX.Q6_K.gguf	Q6_K	2.47GB
Falcon3-3B-Instruct-MLX.Q8_0.gguf	Q8_0	3.2GB

Original model description:

base_model: tiiuae/Falcon3-3B-Instruct language: - en - fr - es - pt library_name: transformers license: other license_name: falcon-llm-license license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html tags: - falcon3 - mlx

TheBlueObserver/Falcon3-3B-Instruct-MLX

The Model TheBlueObserver/Falcon3-3B-Instruct-MLX was converted to MLX format from tiiuae/Falcon3-3B-Instruct using mlx-lm version 0.20.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("TheBlueObserver/Falcon3-3B-Instruct-MLX")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Downloads last month: 624

GGUF

Model size

3B 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