Fascinating that after years of for me this for me that, literally no one writes 2-3 other words like “i do react frontend” or whatever just for us to know why the results are different

▲

girvo a day ago | parent | next [-]

They also need to tell people what quantisation they're using. Because some 4 bit version is not the same as BF16, no matter what KLD suggests.

	▲	skohan 19 hours ago \| parent [-]
		I'm using the unsloth dynamic Q4 and getting good results. I was running Q5, but Q4 gives more context headroom so I can run two agents in parallel with ~100k context each with 32GB vram.

▲

throwaway240403 a day ago | parent | prev | next [-]

lol, exactly.

▲

skohan a day ago | parent | prev [-]

Your assumption is incorrect.