GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form
-
abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF
Text Generation • 33B • Updated • 3.21k • 27 -
abenzerps/Spark-X2.6-4B-Uncensored-GSQ-RCO-GGUF
Text Generation • 4B • Updated • 776 • 5 -
abenzerps/NeoHorse-1-9B-Uncensored-GSQ-RCO-GGUF
Text Generation • 9B • Updated • 2.96k • 11 -
abenzerps/Nemotron-3.5-Bolt-E4B-GSQ-RCO-GGUF
Text Generation • 8B • Updated • 4.49k • 7