Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
mllm is a fast and lightweight multimodal LLM inference engine designed for mobile and edge devices. It supports Pythonic eager execution, unified hardware backends including Arm CPU, OpenCL GPU, and NPUs, and integrates seamlessly with popular community model checkpoints.
Parse Score