> it can run deepseek flash 1017 pretty well.
What do you mean? DeepSeek Flash 1017 is well over 200GB even at 1 bit quantization, how are you running it locally?
What do you mean? DeepSeek Flash 1017 is well over 200GB even at 1 bit quantization, how are you running it locally?
> Unsloth Desktop + llama.cpp enables ~3x faster DeepSeek-V4.1 inference than other CPU/VRAM/ngram repos. DeepSeek and runs locally on 128GB+ RAM setups or 64GB RAM (slower).