🚨 STOP WHAT YOU ARE DOING AND LOOK AT THESE BENCHMARKS@atomic_chat_hq just unlocked 1.5x faster inference for Gemma 4 on LLaMA.cpp using Multi-Token Prediction.

138 tokens per second on a local 26B model is pure sorcery 👀

Get the code and GGUFs below ↓ https://t.co/o4aF64B5ee

— Charly Wargnier (@DataChaz) 8 mai 2026

STOP WHAT YOU ARE DOING AND LOOK AT THESE BENCHMARKS @atomic_chat_hq just unlocked 1.5x faster inference for Gemma 4 on LLaMA.cpp using Multi-Token Prediction. 138 tokens per second on a local 26B model is pure sorcery Get the code and GGUFs below ↓

→ View original post on X — @datachaz