Make money doing the work you believe in

On Sunday I write about speculative decoding, and immediately we get Qwen3.6 with MTP and support for llama.cpp: huggingface.co/unsloth/…

I just tested it and it looks really promising. I'll report back with some numbers.

@adlrocha - Towards local plug-and-play AI
May 19
at
10:11 AM
Relevant people

Log in or sign up

Join the most interesting and insightful discussions.