4-bit Open on Hugging Face
Parameters
9.0B
Weights (est.)
≈ 6.0 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Ornith-1.0-9B-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- ornith-ai/Ornith-1.0-9B (quantized)
- Vendor
- ornith-ai
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 308 in the last 30 days · 4.1K all time · 9 likes
- Published
- 2026-07-14 · updated 2026-10-18 (24d ago)
- Tags
- qwen3_5, quantized, mixed-precision, 4bit, 8bit, optiq, apple-silicon, vision-language, qwen3.5
Other MLX builds of ornith-ai/Ornith-1.0-9B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Ornith-1.0-9B-4bit | 4-bit | ≈ 6.0 GB | 16 GB+ | 356 |
| Ornith-1.0-9B-OptiQ-4bit (this one) | 4-bit | ≈ 6.0 GB | 16 GB+ | 308 |
| Ornith-1.0-9B-OptiQ-6bit | 6-bit | ≈ 7.3 GB | 16 GB+ | 78 |
| Ornith-1.0-9B-6bit | 6-bit | ≈ 8.2 GB | 16 GB+ | 86 |
| Ornith-1.0-9B-8bit | 8-bit | ≈ 10.4 GB | 16 GB+ | 69 |