Instructions to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M 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 majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_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 majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_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 majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M

Use Docker

docker model run hf.co/majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M

LM Studio
Jan

vLLM

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M

Ollama
How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M with Ollama:
```
ollama run hf.co/majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M
```
Unsloth Desktop

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M

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": "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M with Docker Model Runner:
```
docker model run hf.co/majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M
```

Lemonade

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M

Run and chat with the model

lemonade run user.Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M-Q3_K_M

List all available models

lemonade list

Hermes Agent

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_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 majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_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 "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M:Q3_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"

KV-cache quantization (upstream, no fork needed): llama.cpp/Ollama cover this natively — -ctk q8_0 -ctv q8_0 (~~half KV memory, negligible quality loss) or -ctk q4_0 -ctv q4_0 (~~quarter memory, small quality cost). In Ollama: OLLAMA_KV_CACHE_TYPE=q8_0 with OLLAMA_FLASH_ATTENTION=1.

Nemotron-Cascade-2-30B-A3B — TurboQuant GGUF Q3_K_M

nvidia/Nemotron-Cascade-2-30B-A3B quantized pack, published as Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M.

Method

llama.cpp Q3_K_M quantization.

Release line

Released under the TurboQuant line. RotorQuant and TurboQuant are this project's release labels for this pack, not distinct quantization algorithms — both brand repos carry byte-identical weights. No brand-specific speedup is claimed or measured.

Modality

pipeline_tag: text-generation. This is a Mixture-of-Experts (MoE) model — a subset of experts is active per token; total and active parameter counts differ. This is a llama.cpp GGUF conversion of the text tower; no modality beyond pipeline_tag above is claimed or included.

License

This pack is a derivative of nvidia/Nemotron-Cascade-2-30B-A3B; all credit for the original model, training, and weights belongs to the upstream authors. This repo republishes a quantized conversion of those weights only.

Governed by the nvidia-open-model-license. See the upstream repo and the linked license for the full terms — no license text is reproduced here.

Downloads last month: 32

GGUF

Model size

32B params

Architecture

nemotron_h_moe

Hardware compatibility

3-bit

Model tree for majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M

Base model

nvidia/Nemotron-Cascade-2-30B-A3B

Quantized

(35)

this model