The open‑source llama.cpp library ships version b11471 with extra vocabulary tokens and pre‑built binaries for macOS, iOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team released llama.cpp version b11471. It adds a new set of 30090 plamo fim tokens to the model vocabulary. The release also provides ready‑to‑run binaries for macOS Apple Silicon, macOS Intel, iOS, and several Linux builds (CPU, Vulkan, CUDA 12.8). Users can download the appropriate package from the GitHub release page.
Developers can now run llama.cpp locally on more devices without building from source, saving time and simplifying testing.
Models
The company’s new three‑agent Claude‑based reviewer found 73.43% of core‑claim errors, far above the previous best of 14.81%.
Models
Mistral's new trillion‑parameter model scores 38 on an independent index, but costs more per task than competing open models.
Models
OpenAI reported two influence campaigns that used AI‑generated content to plant false stories in real media and blocked the involved accounts.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
