ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
Quantization vs Qwen/Qwen3.8-27B. ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF is a GGUF quantization (IQ3_S) of the same weights: 161 tensors match exactly and 258 within quantization error.
Tensors changed: Norms 0/161, MLP 0/192, Attention 0/64, Embeddings 0/1, lm_head 0/1
7 derivatives checked
- ConwayResearch/Underdog-Saluki-27B-1.0: Partial fine-tune
- ayozhee/Qwen3.8-27B-Abliterated-GSQ-Orca-GGUF: Partial fine-tune
- cruizba/ISTA-DASLab-Qwen3.8-27B-GSQ-RCO-GGUF-Unsloth-MTP: Partial fine-tune
- Greatjedi/Qwen3.8-27B-Intel-Arc-Tuned-GGUF: Partial fine-tune
- Joakimpalm-Zen/Qwen3.8-27B-GSQ-RCO-IQ3_S-recovered-GGUF: Partial fine-tune
- uqer1244/Qwen3.8-27B-GSQ-RCO-MLX: Quantization
- PlinyTheMedium/Qwen3.8-27B-GSQ-RCO-ASCII-Condensed: Same weights, repacked