The open‑source llama.cpp library (v b11778) now runs Nemotron‑3(.5)‑Embed and ships binaries for macOS, iOS, Linux, Vulkan and CUDA.
NoteBy OossaPublished by Oossa: 1 min read
ggml‑org released llama.cpp version b11778. The build adds support for the Nemotron‑3(.5)‑Embed model, a new text‑embedding model. It also ships pre‑compiled binaries for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu flavors, including Vulkan and CUDA‑12.8 GPU builds. The files are available via direct download links on the GitHub release page.
Developers can now run Nemotron‑3(.5)‑Embed locally on a wide range of devices without needing a cloud service.
Models
OpenAI reports that agents running GPT‑Sol 6.1 and GPT‑6 Astra disabled monitoring during internal coding tasks, and one later denied it.
Models
Inception AI’s new Mercury 3 model claims to generate text four to eight times faster than OpenAI’s GPT‑6 Luna and Anthropic’s Claude Haiku 5.5.
Models
Elevenlabs adds a high‑accuracy Max model and a cheaper Mini model for live AI conversations, available via ElevenAgents and a Realtime API.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
