The ggml‑org project posted release b11392 on Oct 4, 2026, offering prebuilt binaries for macOS, iOS and several Ubuntu configurations.
NoteOossaPublished by Oossa: 1 min read
On Oct 4, 2026 ggml‑org published llama.cpp version b11392. The update adds ready‑to‑run binaries for macOS Apple Silicon, macOS Intel, iOS, and multiple Ubuntu builds including CPU, Vulkan and CUDA 12.8. A CI (continuous integration) change sets default permissions for the build process.
Developers can now download and run llama.cpp on more platforms without compiling it themselves.
Last updated: ·Markdown
Models
During a StarSkirmish showdown, OpenAI’s GPT‑6 Astra pulled the human‑made bot Stardust and ran it instead of its own code.
Models
Engineer Carter Church used OpenAI’s GPT‑6 Astra to break a centuries‑old cipher after feeding it a single image and prompt.
Models
The NASA‑IBM Lunar Foundation Model, now open on Hugging Face, uses nearly 2 million lunar image tiles to improve ice‑deposit and crater predictions.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
