8-bit Open on Hugging Face
Parameters
2.1B
Weights (est.)
≈ 2.6 GB
Mac memory (est.)
8 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/typhoon-ocr1.5-2b-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- typhoon-ai/typhoon-ocr1.5-2b (quantized)
- Vendor
- typhoon-ai
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 133 in the last 30 days · 616 all time · 0 likes
- Published
- 2026-06-26 · updated 2026-06-26 (4mo ago)
- Languages
- en, th
- Tags
- qwen3_vl, OCR, vision-language, document-understanding, multilingual, mlx-vlm