Instructions to use yunusemrejr/kiwimind 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 yunusemrejr/kiwimind 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 yunusemrejr/kiwimind # Run inference directly in the terminal: llama cli -hf yunusemrejr/kiwimind
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf yunusemrejr/kiwimind # Run inference directly in the terminal: llama cli -hf yunusemrejr/kiwimind
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 yunusemrejr/kiwimind # Run inference directly in the terminal: ./build/bin/llama cli -hf yunusemrejr/kiwimind
Use Docker
docker model run hf.co/yunusemrejr/kiwimind
- Llama new
- LM Studio
- Jan
- Ollama
How to use yunusemrejr/kiwimind with Ollama:
ollama run hf.co/yunusemrejr/kiwimind
- Unsloth Desktop
- Pi
How to use yunusemrejr/kiwimind with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf yunusemrejr/kiwimind
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": "yunusemrejr/kiwimind" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use yunusemrejr/kiwimind with Docker Model Runner:
docker model run hf.co/yunusemrejr/kiwimind
- Lemonade
How to use yunusemrejr/kiwimind with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull yunusemrejr/kiwimind
Run and chat with the model
lemonade run user.kiwimind-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use yunusemrejr/kiwimind with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf yunusemrejr/kiwimind
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 yunusemrejr/kiwimind
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use yunusemrejr/kiwimind with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf yunusemrejr/kiwimind
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 "yunusemrejr/kiwimind" \ --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"
Kiwi Mind for KiwiBro
The native Kiwi Mind pack lives in candidate/. The KiwiBro desktop and CLI fetch it there. The files total 6.02 GB and include a Q4_K_M trunk, a matching vision projector, and a Q8_0 draft head. The trunk uses activation-selected feed-forward width 8,192 across 42 layers.
The checked runtime supports chat, image input, structured tools, and memory. On compatible CPUs the draft head proposes tokens and the trunk verifies them. Manifest Β· Ryzen hatch replay
KiwiBro source and documentation Β· Archived Spark and Qwen releases
- Downloads last month
- 327
We're not able to determine the quantization variants.