Instructions to use Grawnch/TokenWing-Model-Assets 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 Grawnch/TokenWing-Model-Assets 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 Grawnch/TokenWing-Model-Assets # Run inference directly in the terminal: llama cli -hf Grawnch/TokenWing-Model-Assets
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Grawnch/TokenWing-Model-Assets # Run inference directly in the terminal: llama cli -hf Grawnch/TokenWing-Model-Assets
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 Grawnch/TokenWing-Model-Assets # Run inference directly in the terminal: ./build/bin/llama cli -hf Grawnch/TokenWing-Model-Assets
Use Docker
docker model run hf.co/Grawnch/TokenWing-Model-Assets
- Llama new
- LM Studio
- Jan
- Ollama
How to use Grawnch/TokenWing-Model-Assets with Ollama:
ollama run hf.co/Grawnch/TokenWing-Model-Assets
- Unsloth Desktop
- Pi
How to use Grawnch/TokenWing-Model-Assets with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Grawnch/TokenWing-Model-Assets
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": "Grawnch/TokenWing-Model-Assets" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Grawnch/TokenWing-Model-Assets with Docker Model Runner:
docker model run hf.co/Grawnch/TokenWing-Model-Assets
- Lemonade
How to use Grawnch/TokenWing-Model-Assets with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Grawnch/TokenWing-Model-Assets
Run and chat with the model
lemonade run user.TokenWing-Model-Assets-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use Grawnch/TokenWing-Model-Assets with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Grawnch/TokenWing-Model-Assets
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 Grawnch/TokenWing-Model-Assets
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Grawnch/TokenWing-Model-Assets with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Grawnch/TokenWing-Model-Assets
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 "Grawnch/TokenWing-Model-Assets" \ --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
6 days ago
-
Update model card for wv-plugin-v1.3 (F16C + Vec-SVD + CUDA/Repack overlap + ngram-mod / MTP sidecar)
Verified signature3d6a101 -
Add native-GGUF Qwen3.8-Flash-Next blk.48 MTP draft sidecar (2.39 GiB, shared for Sub2.5bpw & 3.5bpw)
Verified signature5f045a4 -
Add WV-v5 Sub2.5bpw H=96 & upgrade WV-v5 3.5bpw H=96 TokenWing manifests
Verified signature5993d0b -
Add WV-v5 Sub2.5bpw H=96 & upgrade WV-v5 3.5bpw H=96 TokenWing manifests
Verified signatureaf624a1 -
Add Qwen3.8-Flash-Next WV-v5 2.26bpw H=96 TokenWing seed & VRAM manifests
Verified signaturec7e4bff
7 days ago
-
Add Qwen3.8-Flash-Next-WV-v5-3.5bpw TokenWing companion assets (.correction, .vram-experts, .layer-order, .usage-seed)
Verified signaturee63b621
11 days ago
-
Upload Ling 3.0 Flash and Flint 40B .correction, .vram-experts.json, and .layer-order.json assets
Verified signaturece08434 -
initial commit
Verified signaturea132c6b