Swift 1.5 is our new model line. We cut down how much the models think, then post-trained them to keep, and in places beat, the base model's scores. It comes in three versions: Qwen3.8-27B, Qwen3.8-Flash-Next and Bonsai 2.
Swift 1.5 Qwen3.8-Flash-Next is UkisAI's reasoning-efficient derivative of Qwen3.8-Flash-Next. It uses 63.4% fewer thinking tokens, with a 1.8x speed up while keeping the accuracy loss <1% vs base on xhigh.
Read the report →Swift 1.5 Qwen3.8-27B is UkisAI's reasoning-efficient derivative of Qwen3.8-27B. It uses 58.5% fewer thinking tokens while scoring 0.35% higher than the base, for a 9.18× speed-up on several tasks.
Read the technical report →Merged ternary weights in 1-bit and 2-bit GGUF. An experimental research release.
Read the announcement →Swift 1.5 is released under the Swift Open License v1.0. Personal, research, educational, evaluation, and commercial use are free for individuals and organizations with gross annual revenue, including affiliates, of up to US$1,000,000. Above that threshold, commercial use requires a separate Swift Enterprise License. Contact us for terms.
The base models' own licenses still apply. Swift Bonsai 2 is released under Apache-2.0.