@googlegemma: Check out original post by @ivanfioravanti here:
Summary
A demonstration of the Gemma 4 E4B AI model running locally on an iPad using Apple MLX, showcased as an engaging application for children.
View Cached Full Text
Cached at: 08/20/26, 02:56 AM
Check out original post by @ivanfioravanti here: https://t.co/PJUOUPccUP
Ivan Fioravanti ᯅ (@ivanfioravanti): MLX: Tom Riddle’s diary running locally on an iPad powered by Apple MLX with Gemma 4 E4B behind the scene.
Children can go crazy for something like this, no? 🔥
Similar Articles
@rohanpaul_ai: Gemma 4 (specifically its edge-optimized E2B and E4B variants) running fully offline on an iPhone via apps like Locally…
Google’s Gemma 4 E2B/E4B quantized variants now run fully offline on iPhone via apps like Locally AI, leveraging the Apple Neural Engine for on-device inference.
@rohanpaul_ai: So much possibilities for on-device small models. Here @adrgrondin is running Google’s Gemma 4 E2B on iPhone 17 Pro. ~4…
Google's Gemma 4 E2B is demonstrated running on an iPhone 17 Pro via MLX optimization, achieving ~40 tokens/second with 128K context and offline thinking mode for coding and math.
@ivanfioravanti: Autoresearch from @karpathy in action locally using gemma-4-26b-a4b-it-6bit with oMLX on an M5 Max to train Gemma 4 E2B…
Developer Ivan Fioravanti demonstrates running Andrej Karpathy's autoresearch project locally with a 6-bit quantized Gemma-4-26B model on Apple Silicon, suggesting successful training of Gemma 4 E2B IT variant.
Google’s Gemma 4 12B just dropped - here’s how to run it locally on your Mac
Google released Gemma 4 12B, an Apache 2.0 open-source multimodal model supporting text, vision, and audio with a 256K context window. The article provides a guide for running it locally on Macs using Ollama, LM Studio, or llama.cpp.
@MiaAI_lab: I fine-tuned Gemma 4 12B with Fable-5 style reasoning and assistant traces and released it as Gemmable 4 12b. **Availab…
Mia-AiLab released Gemmable 4 12B, a fine-tuned version of Google's Gemma 4 12B model using Fable-5 style reasoning and assistant traces, available in GGUF and MLX formats for local inference.