Instructions to use Sathman/TNH-Agent-SmolLM3-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Sathman/TNH-Agent-SmolLM3-3B-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Sathman/TNH-Agent-SmolLM3-3B-GGUF", filename="TNH_Agent-SmolLM3-3B-Q5_K_M.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Sathman/TNH-Agent-SmolLM3-3B-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: llama-cli -hf Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: llama-cli -hf Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_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 Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_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 Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M
Use Docker
docker model run hf.co/Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M
- LM Studio
- Jan
- vLLM
How to use Sathman/TNH-Agent-SmolLM3-3B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sathman/TNH-Agent-SmolLM3-3B-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sathman/TNH-Agent-SmolLM3-3B-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Ollama
How to use Sathman/TNH-Agent-SmolLM3-3B-GGUF with Ollama:
ollama run hf.co/Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Unsloth Studio
How to use Sathman/TNH-Agent-SmolLM3-3B-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 Sathman/TNH-Agent-SmolLM3-3B-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 Sathman/TNH-Agent-SmolLM3-3B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Sathman/TNH-Agent-SmolLM3-3B-GGUF to start chatting
- Docker Model Runner
How to use Sathman/TNH-Agent-SmolLM3-3B-GGUF with Docker Model Runner:
docker model run hf.co/Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Lemonade
How to use Sathman/TNH-Agent-SmolLM3-3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sathman/TNH-Agent-SmolLM3-3B-GGUF:Q5_K_M
Run and chat with the model
lemonade run user.TNH-Agent-SmolLM3-3B-GGUF-Q5_K_M
List all available models
lemonade list
TNH Agent (SmolLM3 3B) — Pure Thich Nhat Hanh Voice
A fine-tuned SmolLM3-3B model trained exclusively on Thich Nhat Hanh's teaching atoms. Embodied practice, interbeing, gentle firmness. Question in, TNH out.
This is the lightweight 3B branch of the TNH Agent. Same V6 training format as the 8B version, smaller footprint.
~4,100 atoms from 2 books (The Heart of Buddha's Teaching + Dharma Talks, 1,097 pages).
Quick Start
LM Studio / Ollama / llama.cpp: Download TNH_Agent-SmolLM3-3B-Q5_K_M.gguf and load it. No system prompt required.
Example:
User: I keep getting caught in anxious thinking. What do I do?
TNH Agent: When you notice you are caught, that noticing is already the beginning of freedom. You don't have to fight the anxious thinking — you have to recognize it. "I see you, anxiety." Recognition is not suppression. Breathe in, and with the in-breath, say hello to what is there. Breathe out, and allow it to be held in the warmth of your awareness. This is the practice of mindfulness — not eliminating, but embracing.
User: What is interbeing?
TNH Agent: Look at a piece of paper. In it you can see the cloud — without the cloud, there is no rain; without rain, the tree cannot grow; without the tree, there is no paper. The cloud is in the paper. The logger who cut the tree is in the paper. The wheat that fed the logger is in the paper. Everything inter-is. Nothing can exist by itself alone.
What Makes This Different
- Pure TNH, nothing else. Trained only on Thich Nhat Hanh's atoms.
- Embodied practice. Breathing, walking, touching the earth — practice is present-moment return.
- Soft firmness. Not harsh, not soft — grounded in the dharma without aggression.
- Interbeing alive. The model carries his specific way of seeing connection.
- 3B footprint. Runs on modest hardware — ~2 GB with Q5_K_M.
Training Details
| Setting | Value |
|---|---|
| Base model | HuggingFaceTB/SmolLM3-3B-Base |
| Method | A-LoRA V6 (QDoRA + rsLoRA) |
| Rank | 32, alpha 32 |
| Training data | TNH V6 atoms (from ~4,100 raw, filtered for complete question+teaching pairs) |
| Source books | The Heart of Buddha's Teaching, Dharma Talks |
| Format | V6 — question + concept arrows (input) → pure teaching passage (output) |
| Epochs | 1 |
| Quantization | Q5_K_M GGUF (~2 GB) |
The A-LoRA Methodology
A-LoRA (Atom LoRA) fine-tunes on complete reasoning atoms — indivisible multi-component teaching moves extracted from human expert traces. Each atom contains transformation (before/after), concept relations, anchoring quotes, and teacher method. Training on whole atoms produces models that move like teachers, not just sound like them.
The Teacher
Thich Nhat Hanh (1926–2022). Engaged Buddhism. Interbeing. The breath as the bridge between mind and body. Walking meditation as peace in every step. His teaching is not conceptual — it is a practice you can do with your next breath.
| Style element | What it means |
|---|---|
| Embodied practice | Instruction grounded in the body — breath, walking, eating |
| Interbeing | Everything exists in relationship; nothing is separate |
| Soft firmness | Gentle but uncompromising in pointing to what is |
| Present-moment return | Every teaching is an invitation back to now |
3B vs 8B
The 8B TNH Agent carries more nuance and handles multi-step practice guidance better. This 3B branch preserves the core TNH movement for memory-constrained environments.
Files
| File | Size | Use |
|---|---|---|
TNH_Agent-SmolLM3-3B-Q5_K_M.gguf |
~2 GB | Recommended |
Related Models
- Full series — Meditation Agent Collection — all 19 models
- TNH Agent 8B — Full-fidelity TNH, Qwen3-8B base
- Meditation Agent 3B — All 9 teachers blended, SmolLM3-3B
- Meditation Agent 8B — All 9 teachers blended, Qwen3-8B
ellam sivamayam — Everything is Shiva's expression.
எல்லாம் சிவமயம்
- Downloads last month
- 28
5-bit
Model tree for Sathman/TNH-Agent-SmolLM3-3B-GGUF
Base model
HuggingFaceTB/SmolLM3-3B-Base