ukisai/Swift1.5-Qwen3.8-Flash-Next
image-text-to-text model by ukisai
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
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. We gave base Qwen3.8-Flash-Next and Swift 1.5 Qwen3.8-Flash-Next the same prompt: Try the game yourself here: https://ukisai.com/swift-games/flash-next Base Qwen3.8-Flash-Next took 8 minutes 52 seconds to build its game. Swift 1.5 took 4 minutes 56 seconds. We made Swift Flash Next efficient by figuring out which tokens were linked to pathological overthinking and penalizing them without "attacking" the reasoning length directly then regained the accuracy with RL and OPD, leading to "compressed" token usage while maintaining accuracy. Swift 1.5 produces shorter reasoning traces. In our testing, we also observe fewer overthinking errors. This release also features our previously mentioned post-training methods adapted specifically for coding and long-horizon agent work such as personal agents, terminal use and software engineering. Our training data…
Read the full model card ↗ · Preview checked 2026-09-29T09:23:09.032Z
Inside the original model card — Document outline
- Swift 1.5 Qwen3.8-Flash-Next
- Demo
- Training approach
- Evaluation
- Efficiency across reasoning efforts
- Quantized models
- How to use
- GGUF download
- UkisAI API
- vLLM
- SGLang
- Transformers
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
ukisai/Swift1.5-Qwen3.8-Flash-Next is a image-text-to-text model repository published by ukisai on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 445
- Cumulative likes
- 53
- Hugging Face trending score
- 53
- Reported safetensors parameters
- 179,999,981,459
- Architecture
- Qwen4ExpForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-09-22T08:54:04.000Z
- Last modified
- 2026-09-24T16:22:00.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.8-Flash-Next
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-29T06:38:06.650Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.