UkisAI PRO

ukisai

17 11

Basher17's profile picture

Xeiyra's profile picture

k1xwl's profile picture

https://ukisai.com

UkisAI

AI & ML interests

None yet

Recent Activity

updated a dataset 2 days ago

ukisai/opsa_sft_50k_v1

published a dataset 3 days ago

ukisai/opsa_sft_50k_v1

updated a dataset 3 days ago

ukisai/opsa_50k_training_v1

View all activity

Organizations

None yet

ukisai 's collections 6

Swift1.5 Flash Next

Swift Flash Next: the next Swift generation. Weights and quantized builds are added here as they are released.

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

Image-Text-to-Text • 180B • Updated Sep 24 • 2.43k • 110
ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF

Image-Text-to-Text • 177B • Updated Sep 24 • 49.6k • 73
ukisai/Swift-1.5-Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 120B • Updated Sep 24 • 1.32k • 23
ukisai/Swift-1.5-Qwen3.8-Flash-Next-W4A16-AWQ

Image-Text-to-Text • 180B • Updated Sep 24 • 453 • 3

Swift 1.5 Ornith 9B

Swift 1.5 Ornith 9B: standalone BF16 weights and GGUF files for llama.cpp.

ukisai/Swift-1.5-Ornith-9B

Image-Text-to-Text • 10B • Updated 9 days ago • 1.39k • 7
ukisai/Swift-1.5-Ornith-9B-GGUF

Image-Text-to-Text • 9B • Updated 9 days ago • 3.08k • 24

Swift 27B

Swift 1.0, UkisAI's original reasoning-efficient model: 58% fewer thinking tokens than Qwen3.8-27B. BF16 weights and every quant.

ukisai/Swift-Qwen3.8-27b

Image-Text-to-Text • 28B • Updated Sep 24 • 2.62k • 639
ukisai/Swift-Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Oct 1 • 491k • 476
ukisai/Swift-Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated Sep 24 • 2.98k • 43
ukisai/Swift-Qwen3.8-27b-BF16-AMD

Image-Text-to-Text • 28B • Updated Sep 24 • 33 • 2

Swift 1.5 27B

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 Oct 3 • 6.37k • 183
ukisai/Swift-1.5-Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Oct 1 • 131k • 260
ukisai/Swift-1.5-4bit-MLX

Text Generation • 28B • Updated Sep 25 • 3.65k • 20
ukisai/Swift-1.5-3bit-MLX-TextOnly

Text Generation • 27B • Updated Sep 24 • 967 • 5

Swift 1.5 ONNX

ONNX Runtime GenAI builds of Swift 1.5 Qwen3.8-27B.

ukisai/Swift-1.5-Qwen3.8-27b-ONNX-BF16

Image-Text-to-Text • Updated about 1 month ago • 2
ukisai/Swift-1.5-Qwen3.8-27b-ONNX-NVFP4

Image-Text-to-Text • Updated about 1 month ago • 1
ukisai/Swift-1.5-Qwen3.8-27b-ONNX-INT8

Image-Text-to-Text • Updated about 1 month ago • 2
ukisai/Swift-1.5-Qwen3.8-27b-ONNX-INT4-Mixed

Image-Text-to-Text • Updated about 1 month ago • 1

Swift Bonsai 2

Swift adaptation of Ternary Bonsai 2 and its GGUF quantizations.

ukisai/Swift-Bonsai-2-GGUF

Text Generation • 27B • Updated Sep 24 • 11.9k • 71

Swift1.5 Flash Next

Swift Flash Next: the next Swift generation. Weights and quantized builds are added here as they are released.

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

Image-Text-to-Text • 180B • Updated Sep 24 • 2.43k • 110
ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF

Image-Text-to-Text • 177B • Updated Sep 24 • 49.6k • 73
ukisai/Swift-1.5-Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 120B • Updated Sep 24 • 1.32k • 23
ukisai/Swift-1.5-Qwen3.8-Flash-Next-W4A16-AWQ

Image-Text-to-Text • 180B • Updated Sep 24 • 453 • 3

Swift 1.5 27B

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 Oct 3 • 6.37k • 183
ukisai/Swift-1.5-Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Oct 1 • 131k • 260
ukisai/Swift-1.5-4bit-MLX

Text Generation • 28B • Updated Sep 25 • 3.65k • 20
ukisai/Swift-1.5-3bit-MLX-TextOnly

Text Generation • 27B • Updated Sep 24 • 967 • 5

Swift 1.5 Ornith 9B

Swift 1.5 Ornith 9B: standalone BF16 weights and GGUF files for llama.cpp.

ukisai/Swift-1.5-Ornith-9B

Image-Text-to-Text • 10B • Updated 9 days ago • 1.39k • 7
ukisai/Swift-1.5-Ornith-9B-GGUF

Image-Text-to-Text • 9B • Updated 9 days ago • 3.08k • 24

Swift 1.5 ONNX

ONNX Runtime GenAI builds of Swift 1.5 Qwen3.8-27B.

ukisai/Swift-1.5-Qwen3.8-27b-ONNX-BF16

Image-Text-to-Text • Updated about 1 month ago • 2
ukisai/Swift-1.5-Qwen3.8-27b-ONNX-NVFP4

Image-Text-to-Text • Updated about 1 month ago • 1
ukisai/Swift-1.5-Qwen3.8-27b-ONNX-INT8

Image-Text-to-Text • Updated about 1 month ago • 2
ukisai/Swift-1.5-Qwen3.8-27b-ONNX-INT4-Mixed

Image-Text-to-Text • Updated about 1 month ago • 1

Swift 27B

Swift 1.0, UkisAI's original reasoning-efficient model: 58% fewer thinking tokens than Qwen3.8-27B. BF16 weights and every quant.

ukisai/Swift-Qwen3.8-27b

Image-Text-to-Text • 28B • Updated Sep 24 • 2.62k • 639
ukisai/Swift-Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Oct 1 • 491k • 476
ukisai/Swift-Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated Sep 24 • 2.98k • 43
ukisai/Swift-Qwen3.8-27b-BF16-AMD

Image-Text-to-Text • 28B • Updated Sep 24 • 33 • 2

Swift Bonsai 2

Swift adaptation of Ternary Bonsai 2 and its GGUF quantizations.

ukisai/Swift-Bonsai-2-GGUF

Text Generation • 27B • Updated Sep 24 • 11.9k • 71