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)→

Original post →

More from Infra

Infra channel →