Text Generation
GGUF
edge0
Mixture of Experts
edge-inference
latent-moe
4-bit precision
agent
coding
cuda
conversational
Instructions to use Edge0/Edge0-145B-NVFP4 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 Edge0/Edge0-145B-NVFP4 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 Edge0/Edge0-145B-NVFP4:BF16 # Run inference directly in the terminal: llama cli -hf Edge0/Edge0-145B-NVFP4:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Edge0/Edge0-145B-NVFP4:BF16 # Run inference directly in the terminal: llama cli -hf Edge0/Edge0-145B-NVFP4:BF16
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 Edge0/Edge0-145B-NVFP4:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf Edge0/Edge0-145B-NVFP4:BF16
Use Docker
docker model run hf.co/Edge0/Edge0-145B-NVFP4:BF16
- Llama new
- LM Studio
- Jan
- vLLM
How to use Edge0/Edge0-145B-NVFP4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Edge0/Edge0-145B-NVFP4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Edge0/Edge0-145B-NVFP4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Edge0/Edge0-145B-NVFP4:BF16
- Ollama
How to use Edge0/Edge0-145B-NVFP4 with Ollama:
ollama run hf.co/Edge0/Edge0-145B-NVFP4:BF16
- Unsloth Desktop
- Pi
How to use Edge0/Edge0-145B-NVFP4 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Edge0/Edge0-145B-NVFP4:BF16
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": "Edge0/Edge0-145B-NVFP4:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Edge0/Edge0-145B-NVFP4 with Docker Model Runner:
docker model run hf.co/Edge0/Edge0-145B-NVFP4:BF16
- Lemonade
How to use Edge0/Edge0-145B-NVFP4 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Edge0/Edge0-145B-NVFP4:BF16
Run and chat with the model
lemonade run user.Edge0-145B-NVFP4-BF16
List all available models
lemonade list
- Hermes Agent
How to use Edge0/Edge0-145B-NVFP4 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Edge0/Edge0-145B-NVFP4:BF16
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 Edge0/Edge0-145B-NVFP4:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Edge0/Edge0-145B-NVFP4 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Edge0/Edge0-145B-NVFP4:BF16
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 "Edge0/Edge0-145B-NVFP4:BF16" \ --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"
Download NOTICE from Edge0/Edge0-145B-NVFP4: direct link, hf CLI and curl.
- Browser
- Download file 2.56 kB
-
https://huggingface.co/Edge0/Edge0-145B-NVFP4/resolve/main/NOTICE
- Command line
-
hf download hf://Edge0/Edge0-145B-NVFP4/NOTICE
-
curl -L -o NOTICE https://huggingface.co/Edge0/Edge0-145B-NVFP4/resolve/main/NOTICE
2.56 kB
| Edge0 Community Model License — third-party and scope notice | |
| Release notice, 12 November 2026. | |
| Edge0-specific rights | |
| Licensor: Edge0, only for rights it owns or is authorized to license. | |
| Commercial contact: info@edge0.ai | |
| Only the Edge0-specific contributions described in release-scope.json, | |
| insofar as Edge0 owns or is authorized to license them, are designated | |
| under the accompanying LICENSE. No claim is made here that the | |
| entire model, every weight, or a mechanical conversion belongs to Edge0. | |
| Qwen base model | |
| Reported base: Qwen/Qwen3.8-Flash-Next | |
| Copyright (c) 2026 Qwen | |
| Applicable upstream license: Qwen Community License 1.0 | |
| Exact unmodified text: third-party/Qwen-LICENSE.txt | |
| Reference revision: 812d96e10a0dd82b69d749e68693698cf6c36daa | |
| Reference verified: 12 November 2026 | |
| License reference metadata: release-scope.json | |
| The model publisher has identified the Qwen license above as applicable. | |
| The reference revision fixes that license text; it is not a representation | |
| of the training or conversion revision used to create the Edge0 models. | |
| No verified training-source commit is asserted in this release record. | |
| Qwen's copyright, permission notice, commercial conditions, definitions, | |
| disclaimers, and applicable-law requirement remain unchanged. The Edge0 | |
| license does not replace them. Required Qwen commercial permission must | |
| come from Qwen or a party authorized by Qwen. The contact in Qwen's text | |
| remains Qwen's contact and must not be replaced with Edge0's address. | |
| Separately licensed code | |
| The existing Edge0 framework is identified as Apache-2.0 in the project | |
| snapshot. The bundled edge0-strata fork retains the MIT license of | |
| Niko1221 and the Strata contributors. Other bundled components retain | |
| their own licenses and notices. This MODEL license does not change them. | |
| These model license files do not distribute that code or replace its NOTICE. | |
| Attribution and relationship | |
| Edge0 acknowledges the work of the Qwen team and the Strata contributors. | |
| Identifying their work describes technical origin only. It does not assert | |
| partnership, endorsement, sponsorship, or authorization beyond their | |
| applicable licenses or a separately verified agreement. | |
| Existing grants | |
| This model license does not revoke prior valid licenses, create exclusive rights | |
| in upstream material, or retrospectively change the conditions of copies | |
| already released under another valid grant. An erroneous metadata label | |
| also cannot grant upstream rights that the publisher did not possess. | |