signal_tag · 4_broadcasts
#gemma-4
// 4 transmissions tagged with #gemma-4
TX_711285· AI
Google releases Gemma 4 QAT models for on‑device AI
Google unveiled Gemma 4 quantization‑aware training models that shrink size by up to 4× and keep accuracy within 1‑2 % of the full‑precision baseline, targeting smartphones and laptops.
TX_538514· AI
Google introduces Gemma 4 12B, an encoder‑free multimodal model
Google unveiled Gemma 4 12B, a 12‑billion‑parameter model that processes text, images and audio without separate encoders. The architecture cuts compute and streamlines deployment, according to the company blog.
TX_315317· AI
Gemma‑4 runs on 2016 Xeon, proving old hardware can still serve AI
A benchmark shows a 2016 Xeon processor can run the Gemma‑4 model with latency comparable to newer CPUs, offering a cheap path for AI inference workloads.
TX_595452· AI
Parlotype adds Gemma 4 with five on-device speech models for Windows
Maksim Demin's Parlotype now supports Gemma 4 alongside Whisper, offering five quantized variants tuned for accuracy, speed, and disk use on Windows .NET