jakeatx/Qwen3.8-Perian-GGUF
Not comparable yet vs jakeatx/slimder-qwen38-ream288-depth32-agentic-ngram50-compact. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (346 of 784/853 match), usually an architecture llama.cpp's name map doesn't cover yet.