Harrison Kinsley(@Sentdex):162M tokens into MiniMax M2.7 running locally w/ Hermes for work, data analysis, and general daily Q&A. I really cannot get over how good M2.7 + Hermes is. One change I made almost a week ago is going with 8bit kv cache. I'd say that's a free move worth making to free up a bunch of memory. Voice mode is also A+. you can config to use whisper locally and local TTS. No more sending endless voice clips to the cloud.

Harrison Kinsley

@Sentdex

gpus and tractors. Neural networks from Scratch book:

Joined May 2013

477 Following 109.9K Followers

Harrison Kinsley@Sentdex

2026.05.16 21:57

162M tokens into MiniMax M2.7 running locally w/ Hermes for work, data analysis, and general daily Q&A. I really cannot get over how good M2.7 + Hermes is. One change I made almost a week ago is going with 8bit kv cache. I'd say that's a free move worth making to free up a bunch of memory. Voice mode is also A+. you can config to use whisper locally and local TTS. No more sending endless voice clips to the cloud.

189

Forward to community

Most Popular Users