Hey, has anyone here used Qwen3.5-27B-NVFP4-GGUF with llama.cpp yet?
Hey! I was wondering if anyone of you have used Qwen3.5-27B-NVFP4-GGUF on RTX5090 on llama.cpp? I have downloaded and tested today Freenixi/AxionML-Qwen3.5-27B-NVFP4-GGUF and it's quite impressive (quality of answers and deffinatelly beter in…