---
license: mit
base_model: deepreinforce-ai/Ornith-1.0-35B
library_name: mlx
tags:
- mlx
- vision
pipeline_tag: image-text-to-text
---

# ToPo-ToPo/Ornith-1.0-35B-mlx-4bit

MLX **4bit** conversion of [`deepreinforce-ai/Ornith-1.0-35B`](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) for Apple Silicon (mlx-vlm).

## Provenance (self-converted from official weights)
- Source: [`deepreinforce-ai/Ornith-1.0-35B`](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) (license: mit)
- Tool: `mlx-vlm 0.6.3` — `mlx_vlm.convert --hf-path deepreinforce-ai/Ornith-1.0-35B --mlx-path . -q --q-bits 4 --q-group-size 64`
- Effective: **4.649 bits/weight**
- Note (MoE): the source stores experts per-expert (`experts.{i}.gate_proj/up_proj/down_proj`), while mlx-vlm expects a fused/stacked `experts.gate_up_proj`. A `sanitize` monkeypatch fused them before conversion (gate then up, stacked over experts).
- Validation: reproduced geometrically exact CAD output in an agentic CAD+FEM pipeline
  (volumes match the reference mlx-community conversion).

## Usage
```python
from mlx_vlm import load, generate
model, processor = load("ToPo-ToPo/Ornith-1.0-35B-mlx-4bit")
```