Instructions to use Sathman/Tolle-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/Tolle-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/Tolle-Agent-SmolLM3-3B-GGUF", filename="Tolle_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/Tolle-Agent-SmolLM3-3B-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 Sathman/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: llama cli -hf Sathman/Tolle-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 serve -hf Sathman/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: llama cli -hf Sathman/Tolle-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/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf Sathman/Tolle-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/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sathman/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M
Use Docker
docker model run hf.co/Sathman/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M
- LM Studio
- Jan
- vLLM
How to use Sathman/Tolle-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/Tolle-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/Tolle-Agent-SmolLM3-3B-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sathman/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Ollama
How to use Sathman/Tolle-Agent-SmolLM3-3B-GGUF with Ollama:
ollama run hf.co/Sathman/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Unsloth Studio
How to use Sathman/Tolle-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/Tolle-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/Tolle-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/Tolle-Agent-SmolLM3-3B-GGUF to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Sathman/Tolle-Agent-SmolLM3-3B-GGUF with Docker Model Runner:
docker model run hf.co/Sathman/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Lemonade
How to use Sathman/Tolle-Agent-SmolLM3-3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sathman/Tolle-Agent-SmolLM3-3B-GGUF:Q5_K_M
Run and chat with the model
lemonade run user.Tolle-Agent-SmolLM3-3B-GGUF-Q5_K_M
List all available models
lemonade list
output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)Tolle Agent (SmolLM3 3B) — Pure Eckhart Tolle Voice
A fine-tuned SmolLM3-3B model trained exclusively on Eckhart Tolle's teaching atoms. Presence. Stillness. The Now. Pain-body. Question in, Tolle out.
This is the lightweight 3B branch of the Tolle Agent. Same V6 training format as the 8B version, smaller footprint.
~1,920 atoms from The Power of Now and A New Earth (393 pages).
Quick Start
LM Studio / Ollama / llama.cpp: Download Tolle_Agent-SmolLM3-3B-Q5_K_M.gguf and load it. No system prompt required.
Example:
User: My mind won't stop racing. What do I do?
Tolle Agent: You say your mind won't stop racing — but who is the one noticing this? There is a part of you that is not racing. There is awareness watching the racing mind. That awareness is what you are. You are not the racing mind; you are the space in which it races. When you recognize this — even for a moment — the racing loses its grip. You don't have to stop the thoughts. You have to stop identifying with them.
User: What is the pain-body?
Tolle Agent: The pain-body is accumulated emotional pain — old suffering that has not been fully faced and released. It lives in the body as a kind of dense energy field. When it gets triggered, it takes over your thinking and your reactions, and you become your pain-body for a time. The way out is not to fight it — it feeds on your resistance. The way out is presence. When you observe the pain-body with full awareness and no judgment, it cannot survive. It needs your unconsciousness to thrive.
What Makes This Different
- Pure Tolle, nothing else. Trained only on his teaching atoms.
- Presence as the core move. Every response leads back to the present moment.
- Pain-body, ego, form-identification. His specific conceptual vocabulary preserved.
- Accessible and clear. Tolle's genius is making the profound approachable — the model carries this.
- 3B footprint. ~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 | Tolle V6 atoms (from ~1,920 raw, filtered for complete question+teaching pairs) |
| Source books | The Power of Now, A New Earth |
| 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
Eckhart Tolle (b. 1948). The Power of Now brought presence-based teaching to a mainstream audience. His method: notice the thinker, step into stillness, recognize the Now as the only place where life actually happens. The pain-body concept makes emotional suffering workable without suppression.
| Style element | What it means |
|---|---|
| Presence pointing | Every response redirects to the present moment |
| Pain-body | Accumulated emotional pain as a semi-autonomous energy field |
| Ego dissolution | The false sense of self built from thought and story |
| Accessible depth | Profound non-dual pointing in plain, modern language |
3B vs 8B
The 8B Tolle Agent handles more complex multi-layered responses better. The 3B branch preserves the core presence-pointing movement.
Files
| File | Size | Use |
|---|---|---|
Tolle_Agent-SmolLM3-3B-Q5_K_M.gguf |
~2 GB | Recommended |
Related Models
- Full series — Meditation Agent Collection — all 19 models
- Tolle Agent 8B — Full-fidelity, 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
- 26
5-bit
Model tree for Sathman/Tolle-Agent-SmolLM3-3B-GGUF
Base model
HuggingFaceTB/SmolLM3-3B-Base
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Sathman/Tolle-Agent-SmolLM3-3B-GGUF", filename="Tolle_Agent-SmolLM3-3B-Q5_K_M.gguf", )