Instructions to use inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF 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("inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF")

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 inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF"

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": "inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF 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 "inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF"

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 inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF

Run Hermes

hermes

MLX LM

How to use inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

NVIDIA-Nemotron-3-Ultra-550B-A55B-6.2bit-INF

See NVIDIA-Nemotron-3-Ultra-550B-A55B in action: demonstration videos

CURRENTLY UPLOADING...

Tested with an M3 Ultra 512 GiB using Inferencer app

Text Inference: ~11.2 tokens/s @ 1000 tokens ~401.5 GiB

Q6.2-INF uses the data-agnostic INF method tuned to yield maximum general accuracy within a 512 GiB memory budget

Quantization (bpw)	Perplexity	Token Accuracy	Missed Divergence
Q4.5	1.35937	89.75%	28.98%
Q4.8	1.26562	93.50%	19.57%
Q4.8-INF	1.21093	97.70%	10.65%
Q5.5	1.24218	94.60%	17.55%
Q6.2-INF	Untested	-	-
Q6.5	1.21875	96.85%	16.03%
Q8.5	1.21875	97.65%	9.92%
Base	1.20312	100.0%	0.000%

Perplexity: Measures the confidence for predicting base tokens (lower is better)
Token Accuracy: The percentage of correctly generated base tokens
Missed Divergence: Measures severity of misses; how much the token was missed by

Quantized with a modified version of MLX

For more details see our demonstration videos or visit nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16.

Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.

Downloads last month: 78

MLX

Hardware compatibility

Quantized

Model tree for inferencerlabs/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6.2bit-INF

Base model

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Quantized

(15)

this model