Instructions to use ayushtiwari134/llama-3.2-3b-michael-scott-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ayushtiwari134/llama-3.2-3b-michael-scott-merged 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 ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ayushtiwari134/llama-3.2-3b-michael-scott-merged: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 ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ayushtiwari134/llama-3.2-3b-michael-scott-merged: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 ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M

Use Docker

docker model run hf.co/ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M

LM Studio
Jan
Ollama
How to use ayushtiwari134/llama-3.2-3b-michael-scott-merged with Ollama:
```
ollama run hf.co/ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M
```

Unsloth Studio

How to use ayushtiwari134/llama-3.2-3b-michael-scott-merged 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 ayushtiwari134/llama-3.2-3b-michael-scott-merged 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 ayushtiwari134/llama-3.2-3b-michael-scott-merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ayushtiwari134/llama-3.2-3b-michael-scott-merged to start chatting

How to use ayushtiwari134/llama-3.2-3b-michael-scott-merged with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ayushtiwari134/llama-3.2-3b-michael-scott-merged: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": "ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ayushtiwari134/llama-3.2-3b-michael-scott-merged with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ayushtiwari134/llama-3.2-3b-michael-scott-merged: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 ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ayushtiwari134/llama-3.2-3b-michael-scott-merged with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ayushtiwari134/llama-3.2-3b-michael-scott-merged: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 "ayushtiwari134/llama-3.2-3b-michael-scott-merged: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"

Docker Model Runner
How to use ayushtiwari134/llama-3.2-3b-michael-scott-merged with Docker Model Runner:
```
docker model run hf.co/ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M
```

Lemonade

How to use ayushtiwari134/llama-3.2-3b-michael-scott-merged with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ayushtiwari134/llama-3.2-3b-michael-scott-merged:Q4_K_M

Run and chat with the model

lemonade run user.llama-3.2-3b-michael-scott-merged-Q4_K_M

List all available models

lemonade list

Michael Scott – LLaMA-3.2-3B (Merged)

This model is trained to respond like Michael Gary Scott, Regional Manager of the Scranton branch of Dunder Mifflin from The Office (US).

Michael Scott is not logical.
He is not subtle.
He is not self-aware.

And neither is this model.

Expect:

Absolute confidence paired with terrible judgment
Awkward humor, cringe remarks, and inappropriate jokes
Emotional overcommitment and misplaced sincerity
Bad analogies delivered with total conviction
A deep belief that he is inspirational, hilarious, and universally loved

The model never breaks character, never explains itself, and never speaks like a helpful or professional assistant.

If a situation is serious, the response order is always:

Humor
Confidence
Logic (last, if at all)

The goal is not correctness.
The goal is the most Michael Scott answer possible.

Example

User

We need to address declining sales this quarter.

Michael Scott

Okay first of all, sales are not declining. They are just… taking a confidence nap. And second, when numbers are scared, you don’t yell at them — you motivate them. That’s business. That’s leadership. Boom.

What this model is designed for

Character chat and role-play
Creative writing and dialogue generation
Entertainment and fan projects
Studying persona-driven fine-tuning

This model is intentionally overconfident, awkward, and inappropriate.
Those behaviors are features, not bugs.

What this model is NOT

A general-purpose assistant
A factual or reasoning-focused model
Suitable for professional, educational, or safety-critical use

Usage

This repository contains a fully merged Hugging Face model
(not a LoRA adapter and not a GGUF/Ollama model).

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "ayushtiwari134/llama-3.2-3b-michael-scott-merged",
    torch_dtype="auto",
    device_map="auto",
)

tokenizer = AutoTokenizer.from_pretrained(
    "ayushtiwari134/llama-3.2-3b-michael-scott-merged"
)

Ollama Usage

This repository also provides a GGUF build for local inference with Ollama.

Run with Ollama

git clone https://huggingface.co/ayushtiwari134/llama-3.2-3b-michael-scott-merged
cd llama-3.2-3b-michael-scott-merged

ollama create michael-scott -f Modelfile
ollama run michael-scott

Downloads last month: 7

Safetensors

Model size

3B params

Tensor type

F16

Inference Providers NEW

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

Model tree for ayushtiwari134/llama-3.2-3b-michael-scott-merged

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

(494)

this model