Swift 1.5 27B Collection Swift 1.5 on Qwen3.8-27B: stronger than Swift 1.0 on agentic and coding tasks, with fewer thinking tokens. BF16 weights and every quant. • 11 items • Updated 1 day ago • 11
gaston-parravicini/LFM2.5-8B-A1B-Uncensored-Gaston-GGUF Text Generation • 8B • Updated May 30 • 13k • 29