8-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
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/MiMo-VL-7B-RL-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- XiaomiMiMo/MiMo-VL-7B-RL (finetune)
- Vendor
- XiaomiMiMo
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- mit
- Downloads
- 86 in the last 30 days · 914 all time · 0 likes
- Published
- 2025-05-31 · updated 2025-05-31 (1y ago)
- Tags
- qwen2_5_vl
Other MLX builds of XiaomiMiMo/MiMo-VL-7B-RL
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MiMo-VL-7B-RL-4bit | 4-bit | ≈ 4.7 GB | 8 GB+ | 90 |
| MiMo-VL-7B-RL-bf16 | bf16 | ≈ 16.6 GB | 24 GB+ | 77 |
| MiMo-VL-7B-RL-8bit (this one) | 8-bit | — | — | 86 |