Instructions to use rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit 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("rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit")

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 rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit"

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": "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit 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 "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit"

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 rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit"

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 "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit" \
  --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"

NVIDIA Nemotron 3.5 Bolt 74B-A9B — MLX 3bit (text)

MLX conversion of nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 for Apple Silicon, built and tested with Rapid-MLX.

Quantization: mixed: routed experts mostly 3-bit (group size 128) with six interior MoE layers at 2-bit, other projections 4-bit, embeddings 8-bit; lm_head, routers and latent projections kept in BF16 (~3.42 bits per weight)
Size: 31.7 GB — recommended for Macs with 48 GB+ unified memory
Modality: text only. The vision tower and projector from the original multimodal checkpoint are not included.
Context: up to 256K tokens (hybrid Mamba/attention, small KV cache)

Requirements

This checkpoint uses the nemotron_h_puzzle architecture (Mamba/MoE/attention hybrid with per-layer heterogeneous latent MoE). It is not loadable by stock mlx-lm at the time of publishing; use Rapid-MLX (support lands with PR #4679; requires the first release that includes it):

curl -fsSL https://rapidmlx.com/install.sh | bash
rapid-mlx serve rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit

The server exposes OpenAI- and Anthropic-compatible APIs with reasoning and tool calling enabled automatically for this model.

License

Original model by NVIDIA, released under the OpenMDW 1.1 license. This conversion inherits the original license terms.

Downloads last month: 979

Safetensors

Model size

74B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

3-bit

Model tree for rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit

Base model

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

Finetuned

nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16

Quantized

(44)

this model