Gemma 4

1. Fable 5 pushed Gemma 4 to 255 tok/s on WebGPU (xcancel.com via hn)

   +8 13w gemma

   Before Fable 5 was shut down, it pushed Gemma 4 to 255 tok/s on WebGPU. Some didn't believe it was real.

2. Gemma 4 E2B running in-browser at 255 tok/s (huggingface.co via hn)

   +6 13w gemma

   Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

3. Gemma 4 for Telephony: From Two AI Models to One – Until I Switched to Chinese (medium.com via hn)

   +3 13w gemma

   9 min read 23 hours ago 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 Press enter or cli…

← all threads