Instructions to use inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB 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 inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

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 inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

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 inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

Use Docker

docker model run hf.co/inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

LM Studio
Jan
Ollama
How to use inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB with Ollama:
```
ollama run hf.co/inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M
```

Unsloth Studio

How to use inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB 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 inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB 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 inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB to start chatting

How to use inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

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": "inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

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 "inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M" \
  --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 inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB with Docker Model Runner:
```
docker model run hf.co/inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M
```

Lemonade

How to use inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

Run and chat with the model

lemonade run user.NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

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 inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB:Q4_K_M

Run Hermes

hermes

Atomic Chat

Nemotron 3.5 Lightning 30B A3B 5GB

The NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 model, quantized to Q4_K_M and split into 5 GB GGUF files.

5GB split

The model has been split using llama-gguf-split (b10237) as follows:

/llama-gguf-split --split-max-size 5G NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_K_M.gguf NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_K_M

Downloads last month: 103

GGUF

Model size

33B params

Architecture

nemotron_h_moe

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for inference-snaps/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-5GB

Base model

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

Quantized

(68)

this model