Run upgraded Gemma 4 with llama.cpp (QAT + MTP)
Gemma 4 gains QAT and MTP support in llama.cpp
AISummary
Run upgraded Gemma 4 with llama.cpp (QAT + MTP)
Post on XView on X
@ggerganov
We’re rolling out some big improvements to Gemma 4, fueled by incredible community feedback and contributions! Here is a breakdown of what’s being fixed and updated in this release: 🧵👇
Source: Georgi Gerganov · x.comPublished · added here