ukisai/Swift-1.5-Qwen3.8-27b

Image-Text-to-Text • 28B • Updated 7 days ago • 2.97k • 93

Note Swift 1.5 (latest). Full BF16 weights. Start here.

ukisai/Swift-1.5-Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated 7 days ago • 90k • 129

Note Swift 1.5 GGUF for llama.cpp, LM Studio and Ollama.

ukisai/Swift-1.5-4bit-MLX

Text Generation • 28B • Updated 5 days ago • 1.53k • 8

Note Swift 1.5, 4-bit MLX for Apple Silicon Macs.

ukisai/Swift-1.5-3bit-MLX-TextOnly

Text Generation • 27B • Updated 7 days ago • 691 • 4

Note Swift 1.5, 3-bit MLX for Apple Silicon Macs. Text only, no vision.

ukisai/Swift-1.5-Qwen3.8-27b-NVFP4

Image-Text-to-Text • 18B • Updated 7 days ago • 2.76k • 9

Note Swift 1.5, NVFP4/FP8 (NVIDIA ModelOpt). Native NVFP4 needs a Blackwell GPU.

ukisai/Swift-1.5-Qwen3.8-27b-INT4

Image-Text-to-Text • 28B • Updated 7 days ago • 5.06k • 3

Note Swift 1.5, INT4 W4A16 (AWQ + GPTQ, compressed-tensors) for vLLM.

ukisai/Swift-1.5-Qwen3.8-27b-W4A16-AWQ

Image-Text-to-Text • 6B • Updated 7 days ago • 1.4k • 4

Note Swift 1.5, AWQ INT4 W4A16.

ukisai/Swift-1.5-Qwen3.8-27b-W4A16-AutoRound

Image-Text-to-Text • 3B • Updated 7 days ago • 868 • 6

Note Swift 1.5, Intel AutoRound INT4 W4A16.

ukisai/Swift-1.5-Qwen3.8-27b-Quark-FP8-dynamic-AMD

Image-Text-to-Text • 28B • Updated 7 days ago • 225 • 1

Note Swift 1.5, AMD Quark FP8 dynamic W8A8 for AMD GPUs.

ukisai/Swift-1.5-5bit-MLX

Text Generation • 28B • Updated 5 days ago • 1.76k • 3

Note 5-bit MLX for Apple Silicon.

ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF

Text Generation • 27B • Updated 7 days ago • 231k • 177

Note GSQ-RCO low-bit GGUF quantizations.