Joakimpalm-Zen/Qwen3.8-27B-GSQ-RCO-IQ3_S-recovered-GGUF

Partial fine-tune vs ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF. Joakimpalm-Zen/Qwen3.8-27B-GSQ-RCO-IQ3_S-recovered-GGUF is a GGUF (IQ3_S/IQ4_XS) of different weights. Partial change: 78% of the weights changed (attention, mlp, other), in 0 of 0 layers.

Tensors changed: lm_head 0/1, Norms 0/209, other 45/289, Attention 151/160, MLP 167/192

On the Hub · Downloads on Model Pulse