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.
-
ukisai/Swift-1.5-Qwen3.8-27b
Image-Text-to-Text • 28B • Updated • 33 • 20 -
ukisai/Swift-1.5-Qwen3.8-27B-GGUF
Image-Text-to-Text • 27B • Updated • 68 • 22 -
ukisai/Swift-1.5-4bit-MLX
Text Generation • 28B • Updated • 13 • 5 -
ukisai/Swift-1.5-3bit-MLX-TextOnly
Text Generation • 27B • Updated • 8 • 2