Instructions to use abenzerps/Holo4-35B-A3B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abenzerps/Holo4-35B-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/Holo4-35B-A3B-MLX")
config = load_config("abenzerps/Holo4-35B-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/Holo4-35B-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/Holo4-35B-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/Holo4-35B-A3B-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use abenzerps/Holo4-35B-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/Holo4-35B-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/Holo4-35B-A3B-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use abenzerps/Holo4-35B-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/Holo4-35B-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/Holo4-35B-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"

Holo4-35B-A3B MLX

MLX quantizations of Hcompany/Holo4-35B-A3B, a 35B mixture-of-experts (MoE, 3B active) vision-language model (VLM) for Computer Use, tool-driven work, and agentic workflows.

Each quantization includes the full multimodal vision tower (333 visual weights + vision_config), enabling native image and screenshot understanding in MLX-VLM, LM Studio, and Apple Silicon workflows.

Upstream benchmarks

Results reported by H Company from evaluations of the original Holo4-35B-A3B model across computer tasks, long workflows, and tool servers.

MLX Files

Quantization	File	Size
4-bit	Holo4-35B-A3B-MLX-4bit	19.00 GB
6-bit	Holo4-35B-A3B-MLX-6bit	27.07 GB
8-bit	Holo4-35B-A3B-MLX-8bit	35.13 GB

Multimodal Architecture

Component	Architecture	Precision
Language Backbone	Qwen3.5 MoE (35B total, 3B active)	Quantized (4/6/8-bit affine, group_size=64)
Vision Tower	Vision Transformer (333 weights)	Full precision (BF16)
Projector	Multimodal cross-attention / MLP	Full precision (BF16)

Vision tower weights and multimodal projectors are preserved in full precision (BF16) to ensure optimal visual comprehension, OCR, and GUI element grounding without degradation.

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="Holo4-35B-A3B-MLX-6bit", subfolder="Holo4-35B-A3B-MLX-8bit")
model_path = "abenzerps/Holo4-35B-A3B-MLX"
subfolder = "Holo4-35B-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/Holo4-35B-A3B-MLX --subfolder Holo4-35B-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/Holo4-35B-A3B-MLX --subfolder Holo4-35B-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/Holo4-35B-A3B-MLX --subfolder Holo4-35B-A3B-MLX-8bit \
    --image screenshot.png \
    --prompt "What action should be taken next to achieve the user goal?"