The open‑source LLM runtime llama.cpp ships version b12343 with a new Qwen‑3.5 conversion tweak and binary builds for macOS, iOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team released llama.cpp version b12343 on 13 Nov 2026. The update merges tensors when converting Qwen‑3.5 models, simplifying model prep. It also drops a conversion test for that model. Pre‑built binaries are now available for Apple Silicon Macs, Intel Macs, iOS, and several Ubuntu CPU targets, including s390x and Vulkan builds.
Developers can now convert Qwen‑3.5 models faster and run llama.cpp on more Linux hardware without building from source.
Models
OpenAI's new ChatGPT Wallet lets its ‘dots’ agents purchase items for U.S. Pro subscribers using tokenized card data.
Models
The AI agent can place phone calls to cable companies, DMVs and restaurants, but many businesses still hang up on the synthetic voice.
Models
The new Gemini 4 Hydrogen model beats the larger Argon on speed, cost and several benchmarks, and is now available to developers and consumers worldwide.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
