{"slug": "brebus-the-models-of-this-hub-on-your-own-computer-in-an-app-written-in-c", "title": "Brebus: the models of this hub on your own computer, in an app written in C", "summary": "Janas released Brebus, an open-source (GPL-3.0) desktop app written in C that runs local models on a user's own machine without cloud or account, with a Linux version out now and Windows to follow. Brebus downloads the 18 JNS models — including Qwen3, Qwen3.5, Qwen3.6, Qwen3.8, Qwen3-Coder, Gemma 4 and Nemotron 3.5 Bolt — from its catalog with SHA-256 checks, and can search Hugging Face for other GGUF repositories and convert the chosen file locally. Janas said its Janas-LLM engine measures memory, CPU, GPU and NPU on model load and streams mixture-of-experts weights from NVMe SSD when they exceed RAM; on a 32 GB Core Ultra 9 185H laptop, Qwen3-Next-80B (48 GB) wrote at 26.4 tok/s versus 3.0 tok/s for llama.cpp under the same conditions.", "body_md": "Today’s release of Janas brings **Brebus**, its app (Linux for now, Windows next): the models of this machine, a chat with them and a server for other programs, in a window of its own. No cloud, no account, open source (GPL-3.0).\n\n**Models from Hugging Face, two ways.** The 18 JNS models of this organization - Qwen3, Qwen3.5, Qwen3.6, Qwen3.8, Qwen3-Coder, Gemma 4, Nemotron 3.5 Bolt - download from Brebus’s catalog, each checked against its SHA-256, with what it asks of your memory shown first. Any other model is searched on the Hub by name: Brebus lists the repositories with GGUF files, each file with its size, and converts the one you pick on your machine.\n\n**An engine that adapts to the machine.** Janas-LLM measures the memory, the CPU, the GPU and the NPU when it opens a model and chooses how to run it: the whole model in memory when it fits; when a mixture of experts is larger than the RAM, the experts each token needs read from the NVMe SSD and the frequent ones kept in memory; a GPU and Intel’s NPU used where they are faster. On a laptop with 32 GB (Core Ultra 9 185H), Qwen3-Next-80B, 48 GB, writes at 26.4 tok/s, where llama.cpp manages 3.0, under the same conditions wherever possible.\n\n**In the chat:**\n\nIn the picture: Qwen3-30B-A3B in Brebus made a mortgage calculator as a React artifact; 250,000 at 3.5% over 25 years gives 1,251.56 a month, as it should.*\n\n[https://github.com/prabanta-dev/janas](https://github.com/prabanta-dev/janas) · release: [https://github.com/prabanta-dev/janas/releases/tag/v2026.11.16](https://github.com/prabanta-dev/janas/releases/tag/v2026.11.16)", "url": "https://wpnews.pro/news/brebus-the-models-of-this-hub-on-your-own-computer-in-an-app-written-in-c", "canonical_source": "https://discuss.huggingface.co/t/brebus-the-models-of-this-hub-on-your-own-computer-in-an-app-written-in-c/191939#post_1", "published_at": "2026-11-16 11:44:27+00:00", "updated_at": "2026-11-16 11:50:16.489127+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "ai-infrastructure", "ai-products", "developer-tools"], "entities": ["Janas", "Brebus", "Janas-LLM", "Hugging Face", "Qwen3", "Qwen3-Next-80B", "llama.cpp", "Core Ultra 9 185H"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/brebus-the-models-of-this-hub-on-your-own-computer-in-an-app-written-in-c", "markdown": "https://wpnews.pro/news/brebus-the-models-of-this-hub-on-your-own-computer-in-an-app-written-in-c.md", "text": "https://wpnews.pro/news/brebus-the-models-of-this-hub-on-your-own-computer-in-an-app-written-in-c.txt", "jsonld": "https://wpnews.pro/news/brebus-the-models-of-this-hub-on-your-own-computer-in-an-app-written-in-c.jsonld"}}