Holo-3.1-4B-MLX-4bit
4-bit MLX quantization of Hcompany/Holo-3.1-4B — H Company's
4B vision-language computer-use agent (UI grounding, mobile/desktop/web
automation), built on Qwen3.5-VL. Converted with mlx-vlm for Apple Silicon and
vision-validated (correctly grounded UI buttons + read on-screen text in testing).
Other quantizations: 4-bit (this) · 8-bit
📚 Part of the Holo-3.1 MLX (computer-use) collection.
| Precision | MLX 4-bit (LM quantized; vision tower kept in higher precision) |
| Type | Vision-language (image-text-to-text) |
| License | Apache 2.0 |
Requirements
Needs mlx-vlm with Qwen3.5-VL support. Qwen3.5-VL landed on mlx-vlm main; the
qwen3_5_vision model-type currently needs a 1-line allow-list addition (fix pending upstream):
pip install -U "git+https://github.com/Blaizzy/mlx-vlm"
# in mlx_vlm/models/qwen3_vl/vision.py, add "qwen3_5_vision" and "qwen3_5_moe_vision"
# to the allowed model_type list (until the official fix lands).
Usage
python -m mlx_vlm.generate --model pipenetwork/Holo-3.1-4B-MLX-4bit \
--image screenshot.png --prompt "What buttons are on screen?" --max-tokens 200
Conversion
python -m mlx_vlm.convert --hf-path Hcompany/Holo-3.1-4B --mlx-path <out> -q --q-bits 4 --q-group-size 64
Converted by pipenetwork with mlx-vlm. Original model Apache-2.0 by H Company; not affiliated.