Downloads · 30 days
12
13% of all-time downloads
OsirisHippocampus-Vision-v7-MLX
osirisbrain/OsirisHippocampus-Vision-v7-MLX
OsirisHippocampus-Vision-v7-MLX is a image-text-to-text model from osirisbrain. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
The Hippocampus — Osiris's visual cortex. A lightweight 3B VLM that processes screenshots, images, and visual input. Runs natively on Apple Silicon via MLX Metal.
All-time downloads
94
Public
Parameters
3.8B
3.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 99%
Parameter types
How the weights are stored.
U323.1B · 82%
Try a prompt
Base models
Model card
From the Hugging Face model README
OsirisHippocampus-Vision-v7-MLX
The Hippocampus — Osiris's visual cortex. A lightweight 3B VLM that processes screenshots, images, and visual input. Runs natively on Apple Silicon via MLX Metal.
Architecture
- Base Model: Qwen2.5-VL-3B-Instruct (3B parameters, vision-language)
- Format: MLX 4-bit quantized (Apple Silicon native)
- Size: ~2.9 GB
- Speed: ~150+ tokens/sec on M2 Pro
- Capabilities: OCR, screenshot analysis, image understanding, visual QA
Usage
from mlx_vlm import load, generate
model, processor = load("osirisbrain/OsirisHippocampus-Vision-v7-MLX")
output = generate(model, processor, "What do you see in this image?", ["screenshot.png"])
Credits
MLX conversion by mlx-community. Original model: Qwen/Qwen2.5-VL-3B-Instruct by Alibaba.
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen2_5_vl
- License
- apache-2.0
- Languages
- en, es, zh
- Created
- Mar 10, 2026
- Updated
- Mar 10, 2026