BenchmarkMay 2025AI Research
EAI 0.9: INT4 LLM Runtime — 11 tok/s on Cortex-M85
EAI's new quantized inference path squeezes a 1.3B-parameter model into 312 MB of flash and runs at interactive speed on a 480 MHz microcontroller. Block-streamed weight loading reduces peak SRAM by 94%.
EAILLMBenchmark
Read