---
license: mit
base_model: deepreinforce-ai/Ornith-1.0-9B
pipeline_tag: image-text-to-text
library_name: mlx
tags: [ornith, qwen3_5, vl, vision-language, gated-deltanet, linear-attention, mlx, mxfp4, osaurus]
---

![Osaurus](osaurus-x-banner.png)

# Ornith-1.0-9B · MXFP4

Official **OsaurusAI** MXFP4 build of [deepreinforce-ai/Ornith-1.0-9B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B) (MIT) — a **vision-language** model on a Qwen3.5 hybrid backbone. Near-lossless 8-bit microscaled FP; runs on Apple Silicon via [Osaurus](https://osaurus.ai) / mlx.

- **~5.3 GB (from ~18.8 GB bf16)** bundle.
- **MXFP8**: microscaled FP4 (group-size 32, 4-bit) on the language-model linear weights; the **vision tower is preserved at fp16**, short-conv kernels and norms kept fp16.
- **Vision-language** (image + text → text).

## Architecture

| | |
|---|---|
| Family | `qwen3_5` (dense, hybrid) |
| Text layers | 32 — **24 Gated-DeltaNet (linear-attention)** + **8 full-attention** |
| Hidden | 4096 · untied lm_head |
| Vision | ViT tower (`model.visual`) preserved fp16 |
| Cache | hybrid (GDN state + KV for attention layers) |

## Usage
```bash
# text
python -m mlx_lm generate --model OsaurusAI/Ornith-1.0-9B-MXFP4 --prompt "Explain a hash map in two sentences."
```
For image+text, load in [Osaurus](https://osaurus.ai) or an MLX-VLM runtime that supports `qwen3_5` vision.

## Provenance
- Base: [deepreinforce-ai/Ornith-1.0-9B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B) © DeepReinforce — MIT (Qwen3.5-based)
- Quantization: Osaurus · MXFP4 (microscaled FP4, group-size 32; vision tower fp16) · eric@osaurus.ai