llama.cpp team and Hugging Face launch Llama: a 1MB desktop app to run open models locally
mervenoyann · x · 2026-10-24
The llama.cpp team and Hugging Face released Llama, a free, open-source 1MB desktop app (menu bar on Mac, system tray on Windows) that runs the latest open models locally and offline.
Three core pieces:
- Local chat: ChatGPT-style browser chat via one click, zero setup
- Local API: OpenAI-compatible API on localhost, so coding agents, editors, and scripts plug right in
- One-click model install: recommends models that fit your machine and picks settings; screenshots show Qwen3.8 27B, gpt-oss 20B, and gemma-4 E4B installed
It replicates the 'ChatGPT plus API' experience on your own computer with models you choose. Linux installs via a single curl command; Brew/Winget and source builds also supported.
Related event: llama.cpp and Hugging Face Launch Llama, a 1MB Local AI Desktop App(2 posts)→
More from Infra
- Cloudflare launches Origin Range Requests, cutting R2 p99 TTFB by half — Cloudflare Blog · 2026-10-24
- Tencent's Hy-Nomas world model needs at least 24GB VRAM, dev complains — cocktailpeanut · 2026-10-24
- kapitsa: hand-written Metal inference engine hits 140 tok/s on Qwen3.8-27B for local OpenAI/Anthropic APIs — DotaMate · 2026-10-24
- Humansand Speeds Up NVFP4 Decode Kernel by Up to 10% While Improving Accuracy — noahdgoodman · 2026-10-24
- Recursive's 40B Flint Hits ~200 tok/s on M3/M5 Ultra via MLX-VLM with Fused Metal Kernels — timshi_ai · 2026-10-24
- Cloudflare launches post-quantum GeoKey Manager for geo-fenced key decryption — Cloudflare Blog · 2026-10-24