q4 or q5 quantization.
Edit: Actually you'd want q3 to fit a 200B model into 128GB of RAM. e.g. this one is about 140GB https://huggingface.co/lmstudio-community/DeepSeek-V2.5-GGUF...
Edit: Actually you'd want q3 to fit a 200B model into 128GB of RAM. e.g. this one is about 140GB https://huggingface.co/lmstudio-community/DeepSeek-V2.5-GGUF...
(Isn't that kind of like saying you can do real-time 4k encoding when you actually mean it can do real-time 720p encoding and then interpolate the missing pixels?)