very awesome

loads and runs browser-use on a single r9700 32gb, needed a gguf to run on lmstudio

larger quants work fine on a w6800 + r9700, though I didn't immediately notice a performance difference

GGUF

Model size

31B params

Architecture

qwen3vlmoe

Hardware compatibility

4-bit

6-bit

8-bit

16-bit

Model tree for sky-mighty/bu-30b-a3b-preview-quantized

Base model

Finetuned

Quantized

(4)

this model