Instructions to use Edge0/Edge0-120B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Edge0/Edge0-120B-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/Edge0-120B-NVFP4
# Run inference directly in the terminal:
llama cli -hf Edge0/Edge0-120B-NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Edge0/Edge0-120B-NVFP4
# Run inference directly in the terminal:
llama cli -hf Edge0/Edge0-120B-NVFP4

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/Edge0-120B-NVFP4
# Run inference directly in the terminal:
./build/bin/llama cli -hf Edge0/Edge0-120B-NVFP4

Use Docker

docker model run hf.co/Edge0/Edge0-120B-NVFP4

Llama new
LM Studio
Jan

vLLM

How to use Edge0/Edge0-120B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Edge0/Edge0-120B-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/Edge0-120B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Edge0/Edge0-120B-NVFP4

Ollama
How to use Edge0/Edge0-120B-NVFP4 with Ollama:
```
ollama run hf.co/Edge0/Edge0-120B-NVFP4
```
Unsloth Desktop

How to use Edge0/Edge0-120B-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/Edge0-120B-NVFP4

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Edge0/Edge0-120B-NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Edge0/Edge0-120B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Edge0/Edge0-120B-NVFP4
```

Lemonade

How to use Edge0/Edge0-120B-NVFP4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Edge0/Edge0-120B-NVFP4

Run and chat with the model

lemonade run user.Edge0-120B-NVFP4-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Edge0/Edge0-120B-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/Edge0-120B-NVFP4

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://127.0.0.1:8080/v1
hermes config set model.default Edge0/Edge0-120B-NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Edge0/Edge0-120B-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/Edge0-120B-NVFP4

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://127.0.0.1:8080/v1 \
  --custom-model-id "Edge0/Edge0-120B-NVFP4" \
  --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"

Edge0-120B-NVFP4

File size: 1,532 Bytes

335a604
d672813
335a604

{
  "model_name": "edge0-120b-fp4",
  "display_name": "Edge0-120B",
  "family": "Edge0",
  "base_model": "Qwen3.8-Flash-Next",
  "architecture": "latent sparse MoE",
  "params": "120B",
  "active_params": "6.1 B",
  "layers": 48,
  "experts": 512,
  "experts_per_token": "10 routed + 1 shared",
  "latent_dim": 1280,
  "context": 262144,
  "build": "NVFP4",
  "weights": "32.96 GiB",
  "pack_format": "strata pack index v3",
  "exe": "strata",
  "args": [
    "--pack",
    ".",
    "--native",
    "./model-skeleton.gguf",
    "--native-dense-gguf",
    "./model-skeleton.gguf",
    "--ple-gguf",
    "./ple-fp8.gguf",
    "--ple-io",
    "direct",
    "--expert-profile",
    "./profile.bin",
    "--expert-cache",
    "auto",
    "--prefill",
    "auto",
    "--pcie-frac",
    "0.1",
    "--spec",
    "4",
    "--spec-min-p",
    "0.5",
    "--mtp",
    "./mtp",
    "--max-context",
    "131072",
    "--kv",
    "int8",
    "--kv-resident",
    "32768",
    "--vram-reserve-mib",
    "700",
    "--pool-workers",
    "24",
    "--pcie-mode",
    "dma"
  ],
  "cwd": ".",
  "tokenizer": "./tokenizer",
  "log": "./serve.log",
  "port": 8122,
  "gpu": 0,
  "gpus_asked": true,
  "env": {
    "STRATA_LATENT_DENSE": "./latent_dense_q4.bin",
    "STRATA_LATENT_DENSE_FMT": "4",
    "STRATA_LATENT_A": "./experts.bin",
    "STRATA_LATENT_LABELS": "./labels.bin",
    "STRATA_EMBED_VRAM": "1",
    "STRATA_LATENT_FUSED": "1",
    "STRATA_LATENT_FUSED_DU": "1",
    "STRATA_LATENT_U_GPU": "1",
    "STRATA_LAT_FUSED_Q3K": "0"
  }
}