BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

llama.cpp Adds Gemma 4 Audio Stream Support

Nov 9, 2026, first seen via Training & inference tooling releases

llama.cpp release b12237 adds Gemma 4 audio-stream input support and restricts realtime embeddings to audio-generation paths.

Read the original at github.comOpens the publisher's site in a new tab

More in Open-weight & owned stack

Google releases open-source TPU Sync inference systemNov 9Nota Cuts Kimi K3.1 Pro GPU CostsNov 10AI-Built Adobe Clones Gain Rapid Open-Source AdoptionNov 9Asahi Linux Switches Code License From MITNov 9Research Demonstrates Privacy Attacks Against Federated LoRANov 9