News for hackers. Stuff that matters.
Re:Show HN: We made our own inference engine for Apple Silicon by homarp on Tuesday July 15, 2025 @11:36AM (#44572261)
Can you explain the type of quantization you support?

would https://docs.unsloth.ai/basics/kimi-k2-how-to-run-locally be faster with mirai?

Re:Show HN: We made our own inference engine for Apple Silicon by AlekseiSavin on Tuesday July 15, 2025 @12:01PM (#44572552)
right now, we support AWQ but are currently working on various quantization methods in https://github.com/trymirai/lalamo