> 1.58bit quantization
of course we can run any model if quantize it enough. but I think the OP was talking about the unquantized version.
> 1.58bit quantization
of course we can run any model if quantize it enough. but I think the OP was talking about the unquantized version.
Oh you can still run them unquantized! See https://docs.unsloth.ai/basics/llama-4-how-to-run-and-fine-t... where we show you can offload all MoE layers to system RAM, and leave non MoE layers on the GPU - the speed is still pretty good!
You can do it via `-ot ".ffn_.*_exps.=CPU"`
Thanks, I'll try it! I guess "mixing" GPU+CPU would hurt the perf tho.