Running XIAOMI-OCR-0 natively in looksneat
XIAOMI's 0.8B OCR model runs through Rust and MLX in a 645 MB package. A synthetic invoice shows the first integration's text recognition and prompt-driven extraction.
#mlx
4 posts
-
-
Neat discoveries in AI: why I built three local runtimes
Decision models, local speech, and a camera that misread my gestures. The tools I demonstrated at Data Berlin, why I built them, and what their outputs actually mean.
#tools · #ai · #rust · #mlx · #text-to-speech · #computer-vision
-
I benchmarked seven local decision models on 22,270 questions
Seven open decision models produced different results for classification, moderation, and scoring. I measured latency and memory, then published every probability needed to check the results.
#tools · #ai · #rust · #mlx · #benchmarks
-
My terminal now has a 40-millisecond gut feeling
TypeSafe's new model answers questions without writing a single word. An open-weight counterpart now does the same on my Mac in 40 milliseconds, and one of my first tests showed where it stops being trustworthy.
#tools · #ai · #rust · #mlx · #coding-agents