lg4/Qwen3.8-27B-NVFP4-MTP-GGUF
Not comparable yet vs unsloth/Qwen3.8-27B-NVFP4. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (590 of 1968/1202 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs unsloth/Qwen3.8-27B-NVFP4. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (590 of 1968/1202 match), usually an architecture llama.cpp's name map doesn't cover yet.