News for hackers. Stuff that matters.
Re:The new skill in AI is not prompting, it's context engine... by v3ss0n on Tuesday July 01, 2025 @03:53PM (#44437445)
That is true too. But I found Qwen3 14B with 8bit quant fair better than 32B with 4b quant . Both kvcache at 8bit. ( i enabled thinking , i will try with /nothink)

There are no comments on this comment yet.