Instructions to use abenzerps/Holotron4-30B-A3B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abenzerps/Holotron4-30B-A3B-MLX with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("abenzerps/Holotron4-30B-A3B-MLX")
config = load_config("abenzerps/Holotron4-30B-A3B-MLX")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use abenzerps/Holotron4-30B-A3B-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 "abenzerps/Holotron4-30B-A3B-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": "abenzerps/Holotron4-30B-A3B-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use abenzerps/Holotron4-30B-A3B-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 "abenzerps/Holotron4-30B-A3B-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 abenzerps/Holotron4-30B-A3B-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use abenzerps/Holotron4-30B-A3B-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 "abenzerps/Holotron4-30B-A3B-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 "abenzerps/Holotron4-30B-A3B-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"

Holotron4-30B-A3B MLX

MLX quantizations of Hcompany/Holotron4-30B-A3B, a 30B hybrid NemotronH MoE vision-language model (VLM) for Computer Use, tool-driven work, and agentic workflows.

Upstream benchmarks

Holotron4 improves over its base model, Nemotron 3 Nano Omni, on GUI workflows and in environments with MCP tools, APIs, or code sandboxes. Gains are absolute percentage points.

Benchmark	Interface	Nemotron 3 Nano Omni	Holotron4-30B-A3B	Gain
OSWorld	GUI	21.0	76.3	+55.3
OSWorld 2.0	GUI and code	0.2	7.9	+7.7
AutomationBench	MCP	19.4	35.6	+16.2
PinchBench	Terminal	84.7	88.6	+3.9
ALE (Linux, code)	Terminal	0.6	8.5	+7.9

MLX Files

Quantization	File	Size
4-bit	Holotron4-30B-A3B-MLX-4bit	18.30 GB
6-bit	Holotron4-30B-A3B-MLX-6bit	25.82 GB
8-bit	Holotron4-30B-A3B-MLX-8bit	33.33 GB

Usage with MLX-VLM

Installation

pip install -U mlx-vlm

Python API

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load 4-bit (or subfolder="Holotron4-30B-A3B-MLX-6bit", subfolder="Holotron4-30B-A3B-MLX-8bit")
model_path = "abenzerps/Holotron4-30B-A3B-MLX"
subfolder = "Holotron4-30B-A3B-MLX-4bit"

model, processor = load(model_path, subfolder=subfolder)
config = load_config(model_path, subfolder=subfolder)

prompt = "Describe the user interface elements shown in this screenshot."
image = ["screenshot.png"]

formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=len(image)
)

output = generate(model, processor, formatted_prompt, image, verbose=True)
print(output)

Command Line Interface

# 4-bit
python -m mlx_vlm.generate \
    --model abenzerps/Holotron4-30B-A3B-MLX --subfolder Holotron4-30B-A3B-MLX-4bit \
    --image screenshot.png \
    --prompt "What action should be taken next to achieve the user goal?"

# 6-bit
python -m mlx_vlm.generate \
    --model abenzerps/Holotron4-30B-A3B-MLX --subfolder Holotron4-30B-A3B-MLX-6bit \
    --image screenshot.png \
    --prompt "What action should be taken next to achieve the user goal?"

# 8-bit
python -m mlx_vlm.generate \
    --model abenzerps/Holotron4-30B-A3B-MLX --subfolder Holotron4-30B-A3B-MLX-8bit \
    --image screenshot.png \
    --prompt "What action should be taken next to achieve the user goal?"

Source

Downloads last month: -; Downloads are not tracked for this model. How to track

MLX

Hardware compatibility

Quantized

Model tree for abenzerps/Holotron4-30B-A3B-MLX

Base model

Hcompany/Holotron4-30B-A3B

Quantized

(5)

this model

Collection including abenzerps/Holotron4-30B-A3B-MLX

Holo4

Collection

Holo4 model family releases, including GGUF and MLX conversions. • 6 items • Updated 7 days ago