The open‑source LLM runtime adds fresh pre‑built packages for Apple Silicon, Intel Macs, Ubuntu CPUs, Vulkan and CUDA 12.8.
NoteBy OossaPublished by Oossa: Last updated: 1 min read
ggml‑org has published the b11539 release of llama.cpp, the lightweight LLM runner that works on many devices. New binary archives are available for macOS Apple Silicon, macOS Intel, iOS XCFramework, and several Ubuntu builds covering CPU, Vulkan and CUDA 12.8. The download links are posted on the GitHub release page.
Developers can now run llama.cpp locally on more hardware without building it themselves.
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.
