Lukas Wesemann

@lukas-wesemann · 3 works

Builds fast inference engines for LLMs, benchmarking against llama.cpp and MLX.

Recent posts by Lukas Wesemann

• Compute:Arena - Community submitted benchmarks for Local AI Discussion | Link · Product · producthunt.com
• Local - Zero (!) friction local AI for your Mac Discussion | Link · Product · producthunt.com
• BaseRT - 6.4x faster than llama.cpp, 3.9x faster than MLX Discussion | Link · Product · producthunt.com

Topics Lukas Wesemann posts about

• Llama on Instagram - 1 post · Best Llama creators