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/Sage-A1.5-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- InternScience/Sage-A1.5 (quantized)
- Vendor
- InternScience
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 1.3K in the last 30 days · 1.3K all time · 5 likes
- Published
- 2026-10-22 · updated 2026-10-30 (12d ago)
- Tags
- qwen3_5_moe, optiq, quantized, mixed-precision, 4bit, 8bit, qwen3.6, agentic, tool-use, code, vision-language-model, apple-silicon