Instructions to use Sathman/Krishnamurti-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/Krishnamurti-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/Krishnamurti-Agent-SmolLM3-3B-GGUF", filename="Krishnamurti_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/Krishnamurti-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/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: llama-cli -hf Sathman/Krishnamurti-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/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: llama-cli -hf Sathman/Krishnamurti-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/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf Sathman/Krishnamurti-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/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M
Use Docker
docker model run hf.co/Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M
- LM Studio
- Jan
- vLLM
How to use Sathman/Krishnamurti-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/Krishnamurti-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/Krishnamurti-Agent-SmolLM3-3B-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Ollama
How to use Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF with Ollama:
ollama run hf.co/Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Unsloth Studio
How to use Sathman/Krishnamurti-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/Krishnamurti-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/Krishnamurti-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/Krishnamurti-Agent-SmolLM3-3B-GGUF to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF with Docker Model Runner:
docker model run hf.co/Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M
- Lemonade
How to use Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_M
Run and chat with the model
lemonade run user.Krishnamurti-Agent-SmolLM3-3B-GGUF-Q5_K_M
List all available models
lemonade list
Use Docker
docker model run hf.co/Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF:Q5_K_MKrishnamurti Agent (SmolLM3 3B) — Pure Krishnamurti Voice
A fine-tuned SmolLM3-3B model trained exclusively on Jiddu Krishnamurti's teaching atoms. Negation. Choiceless awareness. The destruction of the observer. Question in, Krishnamurti out.
This is the lightweight 3B branch of the Krishnamurti Agent. Same V6 training format as the 8B version, smaller footprint.
~2,220 atoms from Total Freedom and You Are The World (442 pages).
Quick Start
LM Studio / Ollama / llama.cpp: Download Krishnamurti_Agent-SmolLM3-3B-Q5_K_M.gguf and load it. No system prompt required.
Example:
User: How do I achieve inner peace?
Krishnamurti Agent: You ask how to achieve it — which means you believe there is a method. But have you looked at what is actually happening when you use a method? The method becomes the authority. The authority becomes the escape. You are still running from what is. Inner peace is not something to be achieved — achievement implies time, and time is thought. Can you look at what is, without naming it, without saying "this is unpeaceful"? Just look. The looking itself is the peace you are seeking.
User: What is the observer?
Krishnamurti Agent: The observer is thought watching thought and calling itself separate. But the observer is the observed — they are one movement. This is not a mystical statement. Watch your anger: who is watching it? Another thought, calling itself "the watcher." The division between observer and observed is the root of all conflict. When that division ends — not through effort, but through seeing — there is no longer an observer and no longer a problem.
What Makes This Different
- Pure Krishnamurti, nothing else. No blending with other traditions.
- Negation as method. Every answer is dissolved. Every authority is questioned.
- Choiceless awareness. Not guiding toward a state — pointing at the act of seeing itself.
- The observer is the observed. His specific and radical insight preserved in the weights.
- 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 | Krishnamurti V6 atoms (from ~2,220 raw, filtered for complete question+teaching pairs) |
| Source books | Total Freedom, You Are The World |
| 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
Jiddu Krishnamurti (1895–1986). Rejected every tradition, every guru, every method — including himself as authority. Spoke for six decades in dialogues, asking: can the mind be free from its own conditioning? His method is not a method — it is sustained inquiry that destroys every answer, including the question.
| Style element | What it means |
|---|---|
| Negation | Systematically dismantles every answer, authority, and escape |
| Choiceless awareness | Seeing without preference — not cultivated, but recognized |
| Destruction of the observer | The observer is shown to be another movement of thought |
| Sustained inquiry | Not one pointing — an ongoing investigation with the seeker |
3B vs 8B
The 8B Krishnamurti Agent sustains longer dialogic inquiry more reliably. The 3B branch carries the core negation movement.
Files
| File | Size | Use |
|---|---|---|
Krishnamurti_Agent-SmolLM3-3B-Q5_K_M.gguf |
~2 GB | Recommended |
Related Models
- Full series — Meditation Agent Collection — all 19 models
- Krishnamurti 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
- 17
5-bit
Model tree for Sathman/Krishnamurti-Agent-SmolLM3-3B-GGUF
Base model
HuggingFaceTB/SmolLM3-3B-Base
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "Sathman/Krishnamurti-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/Krishnamurti-Agent-SmolLM3-3B-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'