OsirisHippocampus-Vision-v7-MLX

The Hippocampus โ€” 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.

Downloads last month
13
Safetensors
Model size
4B params
Tensor type
U32
ยท
F16
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for osirisbrain/OsirisHippocampus-Vision-v7-MLX

Finetuned
(939)
this model