Instructions to use RobinsAIWorld/kintsugi-models-frozen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use RobinsAIWorld/kintsugi-models-frozen 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 RobinsAIWorld/kintsugi-models-frozen:Q4_K_M # Run inference directly in the terminal: llama cli -hf RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf RobinsAIWorld/kintsugi-models-frozen:Q4_K_M # Run inference directly in the terminal: llama cli -hf RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf RobinsAIWorld/kintsugi-models-frozen:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
Use Docker
docker model run hf.co/RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use RobinsAIWorld/kintsugi-models-frozen with Ollama:
ollama run hf.co/RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
- Unsloth Desktop
- Pi
How to use RobinsAIWorld/kintsugi-models-frozen with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "RobinsAIWorld/kintsugi-models-frozen:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use RobinsAIWorld/kintsugi-models-frozen with Docker Model Runner:
docker model run hf.co/RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
- Lemonade
How to use RobinsAIWorld/kintsugi-models-frozen with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
Run and chat with the model
lemonade run user.kintsugi-models-frozen-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use RobinsAIWorld/kintsugi-models-frozen with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf RobinsAIWorld/kintsugi-models-frozen: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://127.0.0.1:9931/v1 hermes config set model.default RobinsAIWorld/kintsugi-models-frozen:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use RobinsAIWorld/kintsugi-models-frozen with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf RobinsAIWorld/kintsugi-models-frozen: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://127.0.0.1:9931/v1 \ --custom-model-id "RobinsAIWorld/kintsugi-models-frozen: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"
Model card: frozen mirror provenance
Browse files
README.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: upstream-licenses
|
| 4 |
+
license_link: https://huggingface.co/RobinsAIWorld/kintsugi-models-frozen#upstream-sources
|
| 5 |
+
tags:
|
| 6 |
+
- gguf
|
| 7 |
+
- mirror
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Kintsugi frozen model mirror
|
| 11 |
+
|
| 12 |
+
Frozen mirror of the on-device GGUF models used by **Celestial Kintsugi Oracle**
|
| 13 |
+
(`mba.robin.kintsugitarot`). Files are byte-identical server-side copies of the upstream
|
| 14 |
+
repos below (copied 2026-08-12); nothing here changes unless we change it. Model set
|
| 15 |
+
sourced from [AtomicBot-ai/atomic-chat-mobile-data](https://github.com/AtomicBot-ai/atomic-chat-mobile-data) `models.json`.
|
| 16 |
+
|
| 17 |
+
## Upstream sources
|
| 18 |
+
|
| 19 |
+
| File | Upstream | License |
|
| 20 |
+
|---|---|---|
|
| 21 |
+
| LFM2.5-1.2B-Thinking-Q4_K_M.gguf | LiquidAI/LFM2.5-1.2B-Thinking-GGUF | LFM Open License v1.0 |
|
| 22 |
+
| LFM2.5-2.6B-Q4_K_M.gguf | LiquidAI/LFM2.5-2.6B-GGUF | LFM Open License v1.0 |
|
| 23 |
+
| LFM2-700M-Q4_K_M.gguf | LiquidAI/LFM2-700M-GGUF | LFM Open License v1.0 |
|
| 24 |
+
| LFM2-350M-Q4_K_M.gguf / Q5_K_M | LiquidAI/LFM2-350M-GGUF | LFM Open License v1.0 |
|
| 25 |
+
| Q4_K_M/Qwen3.5-4B-*.gguf | sinatras/qwen3.5-4b-split | Apache-2.0 |
|
| 26 |
+
| Qwen3.5-2B-Q4_K_M.gguf | unsloth/Qwen3.5-2B-GGUF | Apache-2.0 |
|
| 27 |
+
| Qwen3.5-0.8B-Q4_K_M.gguf | unsloth/Qwen3.5-0.8B-GGUF | Apache-2.0 |
|
| 28 |
+
| gemma-3-1b-it-Q4_K_M.gguf | ggml-org/gemma-3-1b-it-GGUF | Gemma Terms of Use |
|
| 29 |
+
| SmolLM3-Q4_K_M.gguf | ggml-org/SmolLM3-3B-GGUF | Apache-2.0 |
|
| 30 |
+
| Bonsai-8B-Q1_0.gguf | prism-ml/Bonsai-8B-gguf | MIT |
|
| 31 |
+
| Ternary-Bonsai-8B-Q2_0.gguf | prism-ml/Ternary-Bonsai-8B-gguf | MIT |
|
| 32 |
+
|
| 33 |
+
Each model remains under its upstream license; consult the upstream cards before reuse.
|