bf16 Open on Hugging Face
Parameters
8.3B
Weights (est.)
≈ 16.6 GB
Mac memory (est.)
24 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/olmOCR-7B-0225-preview-bf16 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Qwen/Qwen2-VL-7B-Instruct (finetune)
- Vendor
- Qwen
- Task
- Vision + text
- Quantisation
- bf16
- Licence
- apache-2.0
- Downloads
- 416 in the last 30 days · 2.0K all time · 4 likes
- Published
- 2025-03-03 · updated 2025-03-03 (1y ago)
- Languages
- en
- Tags
- qwen2_vl
Other MLX builds of Qwen/Qwen2-VL-7B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen2-VL-7B-Instruct-abliterated-4bit | 4-bit | ≈ 4.7 GB | 8 GB+ | 67 |
| olmOCR-7B-0225-preview-4bit | 4-bit | ≈ 5.6 GB | 16 GB+ | 45 |
| Qwen2-VL-7B-Instruct-abliterated-6bit | 6-bit | ≈ 6.7 GB | 16 GB+ | 48 |
| olmOCR-7B-0225-preview-6bit | 6-bit | ≈ 7.5 GB | 16 GB+ | 27 |
| Qwen2-VL-7B-Instruct-abliterated-8bit | 8-bit | ≈ 8.8 GB | 16 GB+ | 71 |
| olmOCR-7B-0225-preview-bf16 (this one) | bf16 | ≈ 16.6 GB | 24 GB+ | 416 |
| Qwen2-VL-7B-Instruct-abliterated | — | ≈ 16.6 GB | 24 GB+ | 51 |