llama.app launches: no-code local AI with one-click Gemma 4, MCP support
mervenoyann · x · 2026-09-10
llama.cpp (123.9K GitHub stars) launched llama.app, wrapping llama.cpp in a clean no-code UI: one-click model downloads, clear memory estimates, and support for Gemma 4, Qwen 3.8, GPT-OSS and Gemma 3. Demos show Gemma 4 parsing receipt tables, streaming reasoning logs, and connecting to MCP for web search. Workflow: llama serve, install the pi-llama plugin, and Pi coding agent auto-discovers your local model — no API keys, data stays on-machine. One binary runs from Apple Silicon and RTX 5090 to H100 and DGX Spark.
Related event: llama.cpp Launches llama.app Portal for One-Click Local LLMs(2 posts)→
More from Infra
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Cloud release velocity scores: AWS 95, Azure 90, Google Cloud 82 — DavidLinthicum · 2026-10-27
- Selling a 5090 to scale local inference: one business weighs 5 hardware paths — Anarchaotic · 2026-10-27
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27