Instructions to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit"

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-MLX-5bit

Run Hermes

hermes

OpenClaw new

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit"

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-MLX-5bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Configuration Parsing Warning:Invalid JSON for config file config.json

Nemotron-Cascade-2-30B-A3B — TurboQuant MLX 5bit

nvidia/Nemotron-Cascade-2-30B-A3B quantized pack, published as Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit.

Method

MLX quantization via mlx_lm (5bit, group_size 64).

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.

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: 40

Safetensors

Model size

32B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

Quantized

Model tree for majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit

Base model

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

Finetuned

(24)

this model