Instructions to use mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit 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("mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit")

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 mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit"

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": "mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit 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 "mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit"

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 mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit"

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 "mlx-community/Nemotron-3-Super-120B-A12B-MLX-6bit" \
  --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-Super-120B-A12B-MLX-6bit / README.md

Faisal

Upload README.md with huggingface_hub

7d8ed12 verified 6 months ago

preview code

Raw

History Blame Contribute Delete

2.91 kB

	---
	language: en
	library_name: mlx
	license: other
	license_name: nvidia-open-model-license
	license_link: https://developer.nvidia.com/open-model-license
	pipeline_tag: text-generation
	base_model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
	tags:
	- mlx
	- safetensors
	- nemotron_h
	- nemotron
	- mamba
	- mamba2
	- mixture-of-experts
	- 6bit
	- quantized
	- apple-silicon
	- text-generation
	- conversational
	- reasoning
	- lm-studio
	- custom_code
	---

	# Nemotron-3-Super-120B-A12B — MLX 6-bit

	MLX quantization of [nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16) for Apple Silicon.

	## Key Specs

	\| Detail \| Value \|
	\|---\|---\|
	\| Architecture \| Hybrid Mamba-2 + Transformer Attention + Latent MoE \|
	\| Total Parameters \| 120B \|
	\| Active Parameters \| 12B per token \|
	\| Context Length \| 1M tokens (262,144 default) \|
	\| Experts \| 512 routed, 22 active per token, 1 shared \|
	\| Quantization \| 6-bit affine (6.507 BPW), group size 64 \|
	\| Disk Size \| ~92 GB \|
	\| Peak Memory \| ~98.4 GB \|

	## Requirements

	- Apple Silicon Mac with 128GB+ unified memory
	- `mlx-lm >= 0.31.2` (install from git main for Latent MoE support)

	```bash
	pip install git+https://github.com/ml-explore/mlx-lm.git
	```

	## Usage

	### CLI

	```bash
	mlx_lm.generate \
	--model FF-01/Nemotron-3-Super-120B-A12B-MLX-6bit \
	--prompt "Hello!" \
	--max-tokens 256
	```

	### Python

	```python
	from mlx_lm import load, generate

	model, tokenizer = load("FF-01/Nemotron-3-Super-120B-A12B-MLX-6bit")
	response = generate(model, tokenizer, prompt="Hello!", max_tokens=256)
	print(response)
	```

	### LM Studio

	This model is compatible with [LM Studio](https://lmstudio.ai) on Apple Silicon. Search for `FF-01/Nemotron-3-Super-120B-A12B-MLX-6bit` in the model browser and download directly.

	## Performance

	Tested on M5 Pro Max (128GB):

	\| Metric \| Value \|
	\|---\|---\|
	\| Generation Speed \| ~43.6 tok/s \|
	\| Peak Memory \| 98.4 GB \|

	## About the Architecture

	Nemotron-H is a hybrid architecture combining three components:

	- Mamba-2 layers — efficient state-space model for long-context processing
	- Transformer attention layers — standard multi-head attention (GQA, 32 heads, 2 KV heads)
	- Latent MoE — 512 experts with latent routing, 22 active per token, plus 1 shared expert

	The layer pattern alternates between Mamba (M) and attention with MoE (E) blocks across 88 layers. This hybrid design achieves strong performance with only 12B active parameters per token despite having 120B total.

	## Reasoning Model

	This is a reasoning model that outputs chain-of-thought before the final answer. The model uses `<think>` and `</think>` tags to delineate reasoning.

	## License

	[NVIDIA Open Model License](https://developer.nvidia.com/open-model-license)

	## Credits

	- Base model by [NVIDIA](https://huggingface.co/nvidia)
	- MLX quantization by [FF-01](https://huggingface.co/FF-01)