ukisai/Swift1.5-Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated 7 days ago • 686 • 56

Note Swift + agentic post-training on Qwen3.8-Flash-Next (MoE, 6B active). BF16 weights, 89.6% GPQA-Diamond at xhigh.

ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF

Image-Text-to-Text • 177B • Updated 6 days ago • 18.9k • 42

Note GGUF quantizations for llama.cpp and compatible runtimes.

ukisai/Swift-1.5-Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 120B • Updated 7 days ago • 954 • 13

Note NVIDIA NVFP4 for Blackwell GPUs.

ukisai/Swift-1.5-Qwen3.8-Flash-Next-W4A16-AWQ

Image-Text-to-Text • 180B • Updated 7 days ago • 177 • 2

Note W4A16 AWQ INT4.

ukisai/Swift-1.5-Qwen3.8-Flash-Next-W4A16-AutoRound

Image-Text-to-Text • 73B • Updated 7 days ago • 581 • 5

Note W4A16 AutoRound INT4.