Edge AI model benchmarks
Rigorous, reproducible head-to-head comparisons evaluating inference speed, memory footprint, token fertility, and hardware efficiency against leading open-source models.
NanoForecast v0.5 vs TimesFM →
A 6.5M-parameter edge model beats a 200M-parameter foundation model on 4 of 6 standard benchmarks — after fixing 3 training pipeline bugs with zero architecture changes.
Bharat-Tiny-LLM v3 vs. LLaMA 3 8B: Indic & Hindi Benchmark →
Direct empirical comparison between Eulogik’s Bharat-Tiny-LLM v3 (1.7B) powered by the Brahmi Tokenizer and Meta’s LLaMA 3 8B on Hindi NLP, token compression, and CPU runtime execution.
TinyDoc-VLM-256M vs. Donut: CPU Document AI Benchmark →
Evaluation of document understanding throughput, memory overhead, and OCR accuracy between TinyDoc-VLM-256M and Donut across CPU enterprise servers.
pico-type vs. FastText: 200KB Byte Classifier vs Word Vectors →
Empirical comparison between Eulogik’s pico-type-v02 (200KB ONNX byte-level classifier) and Meta’s FastText on binary size, inference latency, and multi-head routing capability.
NIRNAY 450M vs Jev API: Banking Intent & Decision Calibration →
Direct empirical comparison between Eulogik’s NIRNAY 450M open-weight calibrated decision model and Jev 1.13.0 API on the 3,080-case Banking77 test benchmark.
Model your organizational cost reduction
Use our interactive TCO engine to calculate your exact dollar savings by running Eulogik edge models instead of cloud APIs.