devvexus/marlowe-22b
Full fine-tune vs Qwen/Qwen3.8-27B. devvexus/marlowe-22b is a GGUF (Q4_K/Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 52 of 52 layers.
Tensors changed: Norms 123/131, MLP 156/156, Attention 52/52, Embeddings 1/1, lm_head 1/1