Llama: tiny menu bar app from the llama.cpp team runs open models on Mac
ggerganov · x · 2026-10-27
Developer erusev unveiled Llama, a tiny menu bar app built with the llama.cpp team that runs open models locally on your Mac, demoed in a 35-second video. The repost by llama.cpp creator Georgi Ggerganov signals the project's endorsement, making it a lightweight option for local open-model inference.
More from Infra
- General Compute raises $100M Series A to bet on fast inference demand — _akhaliq · 2026-10-28
- Microsoft's custom Maia chips to make up only ~10% of its AI chip spend by early 2027, says Evercore — Beth_Kindig · 2026-10-28
- YC F26 startup Applied Kin quotes pad-mount transformers in 7 weeks as AI-native manufacturer — ycombinator · 2026-10-28
- Cowboy Space unveils 1MW orbital GPU satellite: 5 GPU racks, 132m span, laser links — BenBajarin · 2026-10-28
- Open-source Zilla adds LLM gateway support: preserving API fidelity across providers — jkriket · 2026-10-28
- Together breaks down the MIGHT stack: composable open-source AI from models to MCP tools — togethercompute · 2026-10-28