Instructions to use ljupco/Nemotron-3-Elastic-30B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ljupco/Nemotron-3-Elastic-30B-MLX 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("ljupco/Nemotron-3-Elastic-30B-MLX")

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 ljupco/Nemotron-3-Elastic-30B-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ljupco/Nemotron-3-Elastic-30B-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ljupco/Nemotron-3-Elastic-30B-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use ljupco/Nemotron-3-Elastic-30B-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "ljupco/Nemotron-3-Elastic-30B-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "ljupco/Nemotron-3-Elastic-30B-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "ljupco/Nemotron-3-Elastic-30B-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use ljupco/Nemotron-3-Elastic-30B-MLX 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 "ljupco/Nemotron-3-Elastic-30B-MLX"

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 ljupco/Nemotron-3-Elastic-30B-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ljupco/Nemotron-3-Elastic-30B-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ljupco/Nemotron-3-Elastic-30B-MLX"

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 "ljupco/Nemotron-3-Elastic-30B-MLX" \
  --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"

Nemotron 3 Elastic 30B - MLX Format (Apple Silicon)

NVIDIA Nemotron 3 Elastic 30B model converted to MLX format for efficient inference on Apple Silicon (Metal).

🚀 Quick Start

Get the MLX model from HuggingFace:

pip install -U "huggingface_hub[cli]"
huggingface-cli download ljupco/Nemotron-3-Elastic-30B-MLX --local-dir ./nemotron-30b-mlx

Run chat (8-bit KV cache by default):

pip install mlx-lm
python chat_mlx.py --model . --max-kv-size 1048576

For larger context with 4-bit KV cache (more memory savings):

python chat_mlx.py --model . --max-kv-size 1048576 --kv-bits 4

📊 Model Details

Format: MLX NVFP4 (4.5 bits/weight)
Size: ~16.5 GB
Context: Up to 1M tokens (design limit, hardware-dependent)
Platform: Apple Silicon (M1/M2/M3) with macOS

💾 Memory Requirements

Config	Peak RAM / Model Size
30B conversion	~59 GB → ~16.5 GB MLX NVFP4
30B inference (1M context, 8-bit KV)	~70-80 GB
30B inference (1M context, 4-bit KV)	~50-60 GB
30B inference (1M context, 16-bit KV)	~90-100 GB

Variant	Size	Platform	Status
Nemotron 3 Elastic 30B NVFP4	30B	Apple Silicon	✅ Ready
Nemotron 3 Elastic 12B NVFP4	12B	Apple Silicon	✅ Slice + convert
Nemotron 3 Elastic 23B NVFP4	23B	Apple Silicon	✅ Slice + convert

🎯 Features

Hybrid Architecture: Mamba-2 + MoE (Mixture of Experts) + Attention layers
Elastic Variants: Supports 12B/23B/30B configurations
Long Context: Designed for up to 1M token context window
Reasoning: Thinking traces enabled by default

📖 Usage

Basic Chat

python chat_mlx.py --model .

Large Text Input

For texts larger than ~4KB:

You> /paste
Now paste your text. After the text is pasted, to process the text, in empty line enter /endpaste
[paste your large text]
/endpaste

Assistant> [processes your text]

In-Chat Commands

/paste - Multi-line input mode for large text
/quit - Exit chat
/reset - Clear conversation history
/thinking on|off - Toggle reasoning traces

🔧 Conversion Tools

This repo includes tools to convert NVIDIA Nemotron 3 Elastic NVFP4 models to MLX format:

convert_to_mlx.py - Converts NVFP4 HuggingFace checkpoints to MLX format
chat_mlx.py - Interactive chat with MLX models on Apple Silicon
zero_shot_slicing.py - Extract 12B/23B variants from 30B elastic checkpoint

The converter handles ModelOpt NVFP4 format:

Loads all shards (fixes cross-shard scale references)
Dequantizes NVFP4 → bfloat16
Loads into MLX Nemotron H model
Re-quantizes to MLX NVFP4 (4.5 bits/weight)

Key fix: Original sharding splits weights and scales across different files. The converter loads all shards before dequantizing to handle this correctly.

🔗 Links

Original Model: https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-NVFP4
Conversion Tools: https://github.com/ljubomirj/nemotron-3-elastic-mlx
NVIDIA License: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/

📝 License

NVIDIA Open Model License. See LICENSE.md for details.

🙏 Acknowledgments

Model Developer: NVIDIA
MLX Framework: Apple MLX team
Conversion: Adapted from mlx-lm Nemotron H implementation

Downloads last month: 264

Safetensors

Model size

32B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for ljupco/Nemotron-3-Elastic-30B-MLX

Base model

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Finetuned

nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-NVFP4

Quantized

(3)

this model