What's the sota? The classic vLLM/llama.cpp? LM Studio? Unsloth studio any good?
vLLM has the best performance if you can fit your entire model into VRAM. llama.cpp is the usual go-to if you're partially loading into RAM. LM Studio is a sensible front-end to llama.cpp. ik_llama.cpp has more advanced CPU quantization strategies than llama.cpp. If you're running super large models mostly from RAM, ktransformers can sometimes be the highest performer, if it works for your model.