7h ago · 12 min read · Building a phone agent on a multimodal LLM: dropping faster-whisper and letting Gemma 4 hear the caller directly — a response-time and reply-accuracy benchmark across English, French, and Mandarin My
Join discussion
May 7 · 6 min read · From the Best GPU for LLM archive. The canonical version has interactive calculators, an up-to-date GPU comparison table, and live pricing. Gemma 4 ships four variants, and the hardware gap between them is enormous. The E2B runs on a potato. The 31B...
Join discussion
Apr 14 · 7 min read · Two weeks ago Google released Gemma 4. I've been running it on everything I have access to — a MacBook Pro M3, an RTX 4090 workstation, and an H100 cloud instance. Here's what I found. TL;DR: The 26B
Join discussionApr 6 · 6 min read · Four days ago, Google released Gemma 4 under Apache 2.0. The headline models are the 31B dense and 26B MoE variants that compete with Llama on Arena AI. But the models I've been running nonstop since release are the ones nobody is talking about: Gemm...
Join discussion
