Instructions to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF 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 Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

Use Docker

docker model run hf.co/Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

LM Studio
Jan

vLLM

How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

Ollama
How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with Ollama:
```
ollama run hf.co/Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF
```

Unsloth Studio

How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF to start chatting

How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

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 "Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF" \
  --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"

Docker Model Runner
How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF
```

Lemonade

How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

Run and chat with the model

lemonade run user.NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

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 Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF

Run Hermes

hermes

Atomic Chat

Lightning is really efficient

by Myric - opened 2 days ago

Discussion

Myric

Owner 2 days ago

•

edited 2 days ago

Hey everybody, I have quants uploading for 3.5 lightning. The coolest part of this model IMHO is the efficient KV cache. That means you can run this with lots of parallel slots (to reduce cache misses on llama) or serve the whole 1M cache size efficiently. A 1M cache costs about 7GB on this model. I did some quick retrieval tests with a full 1M cache and it can retrieve efficiently from that size. I didn't really stress-test how well it could use all that information, but it won't forget your dog's name because it talked to it too long.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment