MXFP4 Open on Hugging Face
Parameters
8.7B
Weights (est.)
≈ 6.4 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/Molmo2-8B-mxfp4 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- allenai/Molmo2-8B (quantized)
- Vendor
- Ai2 · OLMo
- Task
- Vision + text
- Quantisation
- MXFP4
- Licence
- apache-2.0
- Downloads
- 210 in the last 30 days · 210 all time · 0 likes
- Published
- 2026-10-20 · updated 2026-10-20 (22d ago)
- Languages
- en
- Tags
- molmo2, multimodal, olmo, molmo, mxfp4, custom_code