# Low Memory Consumption

Apriel-Nemotron-15b-Thinker is a powerful inference model that performs excellently among models of the same scale. It has efficient memory usage and excellent inference capabilities, making it suitable for various enterprise and academic scenarios.

MEMFOF is a memory-efficient optical flow estimation method designed for full HD videos, combining high precision and low memory usage.

This is the FP8 quantized version of the Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro-2.0 model, quantized from the original BFloat16 format using PyTorch's native FP8 support to optimize inference performance.

Multiple variants based on DeepSeek-R1-Distill-Qwen-1.5B, adapted for LiteRT framework and MediaPipe LLM inference API, deployable on Android platforms.

An efficient large language model optimized with Unsloth's dynamic 4-bit quantization technology, based on Meta Llama 3.2-3B-Instruct

PrunaAI's compressed version of the UniNER-7B-all model, significantly reducing memory usage and energy consumption through quantization techniques while maintaining good named entity recognition capabilities.