4-bit Open on Hugging Face
Parameters
35B
Weights (est.)
≈ 20.4 GB
Mac memory (est.)
32 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-1.5-35B-A3B-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- ornith-ai/Ornith-1.5-35B-A3B (quantized)
- Vendor
- ornith-ai
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 4.9K in the last 30 days · 11K all time · 4 likes
- Published
- 2026-08-25 · updated 2026-10-30 (12d ago)
- Languages
- en
- Tags
- qwen3_5_moe, optiq, quantized, 4bit, mixed-precision, qwen3.5, mixture-of-experts, reasoning, multimodal, vision, long-context, multi-token-prediction
Other MLX builds of ornith-ai/Ornith-1.5-35B-A3B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Ornith-1.5-35B-A3B-OptiQ-4bit (this one) | 4-bit | ≈ 20.4 GB | 32 GB+ | 4.9K |
| Ornith-1.5-35B-A3B-8bit | 8-bit | ≈ 37.7 GB | 48 GB+ | 241 |