cd /news/ai-tools/brebus-the-models-of-this-hub-on-you… · home › topics › ai-tools › article
[ARTICLE · art-170526] src=discuss.huggingface.co ↗ pub= topic=ai-tools verified=true sentiment=↑ positive

Brebus: the models of this hub on your own computer, in an app written in C

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.

read1 min views3 publishedNov 16, 2026

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).

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.

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.

In the chat:

In 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.*

https://github.com/prabanta-dev/janas · release: https://github.com/prabanta-dev/janas/releases/tag/v2026.11.16

── more in #ai-tools 4 stories · sorted by recency
── more on @janas 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/brebus-the-models-of…] indexed:0 read:1min 2026-11-16 · —