Pocket LLMG

Pocket LLMG

Personal Local Text Assistant

0 ratings
Free

Rating summary

Details

Released
September 22, 2026
Updated
November 15, 2026

Features

Pocket LLMG screenshot #1 for iPhone
Pocket LLMG screenshot #2 for iPhone
Pocket LLMG screenshot #3 for iPhone
Pocket LLMG screenshot #4 for iPhone
Pocket LLMG screenshot #5 for iPhone
Pocket LLMG screenshot #6 for iPhone
Pocket LLMG screenshot #7 for iPhone
🖼️Get Icon
Icons↘︎

About

LocalGemma With Gemma E2B Text model support MLX Optimized: High-performance inference using Apple’s MLX framework. Developer-Grade Features: Smart Tool Calling: Seamless, automated function loops by downloading Gemma E2B Text model only. Memory Efficiency: Advanced KV-cache quantization and memory management to prevent crashes. Jinja-Powered: Accurate prompt templating for complex models. Privacy First: 100% local execution. No cloud. No leaks. Experience bleeding-edge, local intelligence. Optimized for Apple Silicon. Users need use Data(Wi-Fi or Cellular) for downloading Gemma E2B Text model from HF site only.
Show more
+1

What's New in Pocket LLMG

1.4

November 15, 2026

Pocket LLMG now works together with Pocket Assistant, in both directions. Send a message in Pocket Assistant and it opens here, generates the reply on this iPhone, and hands the answer back — your chat history is left untouched. While a request is running you will see a short "Generating a reply…" screen instead of your own conversation. If no model is loaded, or this app is already answering, Pocket Assistant is told so and offers a Retry. You can also go the other way: ••• → "Send chat to Pocket Assistant" copies the conversation into the assistant's notes and opens it. Nothing is uploaded: the two apps exchange files through a private container on the device, and those files are deleted as soon as they are read. Both features are optional. The model itself is unchanged.

More

Developer apps