EXL3 models
Collection
76 items โข Updated โข 98
EXL3 quants of Ling-3.1-flash
โ ๏ธ Requires ExLlamaV3 v1.6.3 (or dev branch)
2.10 bits per weight
2.60 bits per weight
3.10 bits per weight
(more bitrates and self-calibrated quants to follow)
Base model
inclusionAI/Ling-3.1-flash