NoromaidxOpenGPT4 1 & 2
#7
by USM-Valor - opened
https://huggingface.co/NeverSleep/NoromaidxOpenGPT4-1-GGUF-iMatrix
https://huggingface.co/NeverSleep/NoromaidxOpenGPT4-2-GGUF-iMatrix
Would love to try these but I think i'd need the smaller quants to be able to fit them on a single 3090.
They are in the queue, static quants will be done first.
Watching them roll in now. Appreciate the fast work!
Indeed, they will end up here:
https://huggingface.co/mradermacher/NoromaidxOpenGPT4-1-i1-GGUF
https://huggingface.co/mradermacher/NoromaidxOpenGPT4-2-i1-GGUF
completely untested as well, of course.
And yes, hf requests immediately get the top place in the queue (so these two overtook 80 other queued models).
mradermacher changed discussion status to closed