Instructions to use CaryPalmer/Kintsugi-27B 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 CaryPalmer/Kintsugi-27B 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 CaryPalmer/Kintsugi-27B:Q4_0 # Run inference directly in the terminal: llama cli -hf CaryPalmer/Kintsugi-27B:Q4_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf CaryPalmer/Kintsugi-27B:Q4_0 # Run inference directly in the terminal: llama cli -hf CaryPalmer/Kintsugi-27B:Q4_0
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 CaryPalmer/Kintsugi-27B:Q4_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf CaryPalmer/Kintsugi-27B:Q4_0
Use Docker
docker model run hf.co/CaryPalmer/Kintsugi-27B:Q4_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use CaryPalmer/Kintsugi-27B with Ollama:
ollama run hf.co/CaryPalmer/Kintsugi-27B:Q4_0
- Unsloth Desktop
- Pi
How to use CaryPalmer/Kintsugi-27B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CaryPalmer/Kintsugi-27B:Q4_0
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": "CaryPalmer/Kintsugi-27B:Q4_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use CaryPalmer/Kintsugi-27B with Docker Model Runner:
docker model run hf.co/CaryPalmer/Kintsugi-27B:Q4_0
- Lemonade
How to use CaryPalmer/Kintsugi-27B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull CaryPalmer/Kintsugi-27B:Q4_0
Run and chat with the model
lemonade run user.Kintsugi-27B-Q4_0
List all available models
lemonade list
- Hermes Agent
How to use CaryPalmer/Kintsugi-27B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CaryPalmer/Kintsugi-27B:Q4_0
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 CaryPalmer/Kintsugi-27B:Q4_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use CaryPalmer/Kintsugi-27B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CaryPalmer/Kintsugi-27B:Q4_0
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 "CaryPalmer/Kintsugi-27B:Q4_0" \ --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"
Commit History
Today
-
Optional DFlash2 drafter (Inco AI, ggml-org Q4_0 GGUF rev cc54a8a3, Apache-2.0) + card for bundle v1.1
Verified signature4e3380b -
Linux bundle v1.0.4
Verified signature04a9f63 -
Card + table: numbers measured on the exact v1.0.3 bundle (shipped settings)
Verified signatureffeaa0b -
Credit the L0xRE-V2 bit allocation (used unchanged); what is ours; fidelity K/V note
Verified signaturebe9343b -
Card: quality pass, links, head-to-head pointer
Verified signature5daedd9 -
Links to the restructured GitHub repo (harnesses/, model/, benchmarks/)
Verified signature2098c04 -
Card + README: bundle v1.0.3, driver 580+, harnesses, verified cards, note on the 7B count
Verified signature7a4231c
Yesterday
-
Card: coding harnesses tested (bundle v1.0.2)
Verified signaturec54eb2f -
Stat card: own numbers only
Verified signature0bdc3c1 -
Kintsugi-27B v1 release card
Verified signatureebd6003 -
Preview card with stats
Verified signatureeade664 -
Stat card
Verified signature0f1bf30 -
Kintsugi-27B-12G.gguf (preview)
Verified signatured8f2164 -
Preview card
Verified signature671fb65 -
initial commit
Verified signature219f7c9