Instructions to use T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf T3cmit0/llama32-3b-emo-gguf:Q4_K_M

Use Docker

docker model run hf.co/T3cmit0/llama32-3b-emo-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use T3cmit0/llama32-3b-emo-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "T3cmit0/llama32-3b-emo-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": "T3cmit0/llama32-3b-emo-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/T3cmit0/llama32-3b-emo-gguf:Q4_K_M

Ollama
How to use T3cmit0/llama32-3b-emo-gguf with Ollama:
```
ollama run hf.co/T3cmit0/llama32-3b-emo-gguf:Q4_K_M
```

Unsloth Studio

How to use T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for T3cmit0/llama32-3b-emo-gguf to start chatting

How to use T3cmit0/llama32-3b-emo-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf T3cmit0/llama32-3b-emo-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": "T3cmit0/llama32-3b-emo-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use T3cmit0/llama32-3b-emo-gguf with Docker Model Runner:
```
docker model run hf.co/T3cmit0/llama32-3b-emo-gguf:Q4_K_M
```

Lemonade

How to use T3cmit0/llama32-3b-emo-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull T3cmit0/llama32-3b-emo-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llama32-3b-emo-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-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 T3cmit0/llama32-3b-emo-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use T3cmit0/llama32-3b-emo-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf T3cmit0/llama32-3b-emo-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 "T3cmit0/llama32-3b-emo-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"

Llama 3.2 3B — Emotional Support (GGUF)

Fine-tune of Llama 3.2 3B Instruct for warm, emotionally supportive conversation in English, quantized to GGUF Q4_K_M for on-device inference with llama.cpp.

These weights power Demo Chat, a fully offline Android chatbot — source code: https://github.com/T3cm0/Chatbot_Movil_Proyecto

Model details


Base model	`unsloth/llama-3.2-3b-instruct-bnb-4bit`
Fine-tuning	SFT with Unsloth + TRL, 2,000 steps
Domain	Emotionally supportive conversation (English)
File	`llama32-3b-emo-Q4_K_M.gguf` (~1.9 GB)
Context window used on device	2,048 tokens
Recommended sampling	`temp 0.6 · top_p 0.9 · top_k 40`

Usage (llama.cpp)

llama-cli -m llama32-3b-emo-Q4_K_M.gguf -c 2048 --temp 0.6 --top-p 0.9

The model uses the standard Llama 3 chat template.

Conversion pipeline

bnb-4bit → fp16 (dequantize) → GGUF f16 (convert_hf_to_gguf.py) → Q4_K_M (llama-quantize). Note: transformers must be pinned to 4.49.0 for the dequantization step.

⚠️ Q4_0 quantizations of this model produced incoherent output with llama-quantize build b10488 (reproduced on x86-64 and ARM). Use Q4_K_M.

License

Derivative of Llama 3.2 — distributed under the Llama 3.2 Community License. Built with Llama.

Downloads last month: 36

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit