jakeatx/slimder-qwen38-reap384-depth40-mb4-5-GGUF
Not comparable yet vs jakeatx/slimder-qwen38-reap384-depth40-mb4-5. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (432 of 1102/1022 match), usually an architecture llama.cpp's name map doesn't cover yet.