§ models · storyline

Fixes Gemma 4 unified FPE on mtmd

llama.cpp fixes a floating-point exception bug in Gemma 4 unified multimodal processing via pull request #24088.

Jun 3 · 22:23:18 · primary fetch3 sourcesupdated Jun 4 · 00:25:03

mtmd: fix Gemma 4 unified FPE (#24088) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (ROCm 7.2) Ubuntu x64 (OpenVINO) Ubuntu x64 (SYCL FP32) DISABLED Android: Android arm64 (CPU) Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.3 DLLs Windows x64 (Vulkan) Windows x64 (SYCL) DISABLED Windows x64 (HIP) openEuler: DISABLED openEuler x86 (310p) openEuler x86 (910b, ACL Graph) openEuler aarch64 (310p) openEuler aarch64 (910b, ACL Graph) UI: UI

read full article on github.com ↗

§ sources3 publications · timeline below

github.comllama.cpp b9496primary22:23:18
venturebeat.comGoogle introduces Gemma 4 12B, a unified, encoder-free open multimodal model that can run locally on devices with 16GB of VRAM or unified memory (Carl Franzen/VentureBeat)00:25:03
marktechpost.comGoogle DeepMind Releases Gemma 4 12B02:00:00

§ how this story moved

02:00:00primary — MarkTechPost publishes the launch post.
22:23:18llama.cpp — Releases picks up coverage.
00:25:03Venturebeat picks up coverage.