webmp3/Sakura-Qwen3.8-Flash-Next-Swift-2.5bit-352E-32GB-GGUF
Partial fine-tune vs ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF. webmp3/Sakura-Qwen3.8-Flash-Next-Swift-2.5bit-352E-32GB-GGUF is a GGUF (IQ2_XS) of different weights. Partial change: 0% of the weights changed (attention, mlp, other), in 0 of 0 layers.
Tensors changed: lm_head 0/1, other 1/223, Norms 0/184, Attention 12/288, MLP 60/331