Ministral-3-3B-vod-search (MLX Optimized)

This model is a fine-tuned version of Ministral-3B-Instruct-2512, specialized in Video On Demand (VOD) and live content. To be used as an orchiestrator in agentic workflow in hybrid VOD and live content search.

It was trained and optimized specifically for Apple Silicon using the MLX framework. The model is fused and quantized to 4-bit, making it extremely fast and memory-efficient on Mac devices.

Downloads last month
52
Safetensors
Model size
0.5B params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Pix111/VOD_search_ministral-3-3b