--- license: other license_name: swift-open-license-1.0 license_link: https://huggingface.co/ukisai/Swift-Qwen3.8-Flash-Next/blob/main/LICENSE library_name: transformers pipeline_tag: image-text-to-text gated: true tags: - qwen3_8 - moe - reasoning - efficient-thinking - token-efficient - post-training - agentic - terminal-bench datasets: - ukisai/Qwen3.8-27B-multi-turn-agent-sft base_model: Qwen/Qwen3.8-Flash-Next base_model_relation: finetune ---
UkisAI
Website  •  Learn more  •  GGUF  •  GSQ-RCO GGUF  •  Evaluation  •  Enterprise licensing
# Swift 1.5 Qwen3.8-Flash-Next Swift 1.5 Qwen3.8-Flash-Next is UkisAI's reasoning-efficient derivative of [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/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. ## Demo We gave base Qwen3.8-Flash-Next and Swift 1.5 Qwen3.8-Flash-Next the same prompt: > Create a 3D endless runner that has the fast, playful feel of Subway Surfers, but make the world and characters your own. I want to run through a lively place, dodge things, collect rewards, and feel the pace build the longer I survive. Make it fun to control and visually memorable. Use your judgment for the setting, mechanics, and little details that make it feel like a real game. Build it so I can launch and play it locally, then tell me how to run it. Try the game yourself here: [https://ukisai.com/swift-games/flash-next](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. ## Training approach 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 is viewable here: https://huggingface.co/datasets/ukisai/Qwen3.8-27B-multi-turn-agent-sft albeit it is not used out of the box, but rather re-sampled, turned into proper RL environments etc. ## Evaluation All scores compare the Qwen3.8-Flash-Next BF16 base with the Swift 1.5 BF16 checkpoint. Token columns report **thinking tokens**, except Terminal-Bench 2.1, which reports **total generated output tokens**.
Benchmark Score Mean tokens Median tokens
BaseSwift 1.5 BaseSwift 1.5 ReductionReduction
General reasoning
GPQA-Diamond89.80%89.60%17,6837,823↓ 55.8%↓ 63.4%
MMLU-Pro87.75%87.20%3,5281,519↓ 57.0%↓ 24.0%
C-Eval93.27%93.60%1,048586↓ 44.1%↓ 7.1%
IFBench73.20%70.13%8,3104,411↓ 46.9%↓ 55.6%
Mathematics
AIME 202698.67%96.67%23,01515,806↓ 31.3%↓ 51.1%
HMMT (Nov 2025)98.00%97.33%25,48716,530↓ 35.1%↓ 54.7%
Multimodal
ERQA70.80%69.30%4,0361,788↓ 55.7%↓ 47.7%
Coding
LiveCodeBench v688.40%90.39%17,8339,849↓ 44.8%↓ 52.0%
Agentic coding
Terminal-Bench 2.1*67.64%69.66%40,59145,428↑ 11.9%↓ 17.9%

* Note: Terminal-Bench 2.1 results for Flash-Next are not an apples-to-apples comparison with Swift 1.5 27B. Flash-Next used default task timeouts, leading to lower scores for both the base model and Swift Flash-Next.

How to reproduce

Serving: BF16 · Qwen3 reasoning parser · context 262,144 · thinking xhigh · MTP disabled.
Sampling: temperature 1.0 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 0 · repetition_penalty 1.
Benchmarks: five seeds (0–4) for the seeded question benchmarks; Terminal-Bench 2.1 uses five attempts per task. LiveCodeBench is full release v6 mean pass@1 over seeds.
Terminal-Bench 2.1: Harbor 0.20.0 / Terminus-2 2.0.0, pinned 89-task dataset, JSON parser, interleaved thinking, temperature 1, top_p 1, 131,072-token server context, 3,600-second LLM call timeout and native per-task limits. Swift used concurrency 8; its context-recovery fix was applied during the run.

BenchmarkOutput cap
GPQA-Diamond100,000
MMLU-Pro100,000
C-Eval16,384
IFBench81,920
AIME 2026250,000
HMMT Nov 2025250,000
ERQA100,000
LiveCodeBench v6100,000
## Efficiency across reasoning efforts GPQA-Diamond at each `reasoning_effort` setting, Swift 1.5 against the base at the same setting:
Reasoning effort Score Mean tokens Median tokens
BaseSwift 1.5 BaseSwift 1.5 ReductionReduction
Xhigh89.80%89.60%17,6837,823↓ 55.8%↓ 63.4%
Medium86.36%83.74%4,1572,483↓ 40.3%↓ 25.1%
Low87.17%84.75%3,9662,645↓ 33.3%↓ 19.7%
At xhigh, Swift 1.5 trails base by 0.20 percentage points while using 55.8% fewer mean and 63.4% fewer median thinking tokens. Medium and low save tokens but also lose 2.62 and 2.42 percentage points respectively. ## Quantized models | Format | Repository | Runtime | | --- | --- | --- | | AWQ INT4 (W4A16) | [Swift-1.5-Qwen3.8-Flash-Next-W4A16-AWQ](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-W4A16-AWQ) | vLLM (`compressed-tensors`) | | AutoRound INT4 (W4A16) | [Swift-1.5-Qwen3.8-Flash-Next-W4A16-AutoRound](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-W4A16-AutoRound) | vLLM (`auto-round`) | | NVFP4 | [Swift-1.5-Qwen3.8-Flash-Next-NVFP4](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-NVFP4) | NVIDIA Blackwell | | GGUF | [Swift-1.5-Qwen3.8-Flash-Next-GGUF](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF) | llama.cpp | | GSQ-RCO GGUF (compact 2–3 bit) | [Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF) | llama.cpp | ## How to use The BF16 checkpoint is about 360 GB, so it needs a multi-GPU node. We evaluated it with tensor parallelism 8. ### GGUF download The **[GGUF version](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF)** is available for compatible llama.cpp-based runtimes. For the smallest files, use the **[GSQ-RCO GGUF version](https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF)**: 66.5–76 GB mixed-precision quants refined for Swift 1.5 Flash-Next. ### UkisAI API Swift 1.5 Flash-Next is served through an OpenAI-compatible API at `https://ukisai.com/api/flash-next/v1`. It is **free for research purposes** and needs no API key. The model id is `flash-next`. ~~~python from openai import OpenAI client = OpenAI(base_url="https://ukisai.com/api/flash-next/v1", api_key="none") response = client.chat.completions.create( model="flash-next", messages=[{"role": "user", "content": "Explain speculative decoding in two sentences."}], ) print(response.choices[0].message.content) ~~~ ~~~bash curl https://ukisai.com/api/flash-next/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model": "flash-next", "messages": [{"role": "user", "content": "Hello, Swift."}]}' ~~~ ### vLLM Use a vLLM build with Qwen3.8-Flash-Next support: ~~~bash vllm serve ukisai/Swift-Qwen3.8-Flash-Next \ --dtype bfloat16 \ --tensor-parallel-size 8 \ --max-model-len 262144 \ --reasoning-parser qwen3 \ --enable-auto-tool-choice \ --tool-call-parser qwen3_xml \ --trust-remote-code \ --port 8000 ~~~ Reasoning effort is set per request through the chat template, for example `"chat_template_kwargs": {"reasoning_effort": "low"}`. `xhigh` is the default; `medium` and `low` are also supported. ### SGLang Alternatively, use an SGLang build with Qwen3.8-Flash-Next support, such as the `lmsysorg/sglang:qwen38flashnext` image: ~~~bash sglang serve \ --model-path ukisai/Swift-Qwen3.8-Flash-Next \ --tp 8 \ --context-length 262144 \ --mem-fraction-static 0.85 \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_coder \ --port 8000 ~~~ Adjust tensor parallelism and context length to your GPU memory. See the base model's [vLLM recipe](https://recipes.vllm.ai/Qwen/Qwen3.8-Flash-Next) and [SGLang cookbook](https://docs.sglang.io/cookbook/autoregressive/Qwen/Qwen3.8-Flash-Next) for installation and hardware-specific settings. ### Transformers Use a Transformers release with Qwen3.8-Flash-Next support: ~~~python import torch from transformers import AutoModelForImageTextToText, AutoProcessor model_id = "ukisai/Swift-Qwen3.8-Flash-Next" processor = AutoProcessor.from_pretrained(model_id) model = AutoModelForImageTextToText.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", ) ~~~ To extend the context to 1,000,000 tokens, follow the YaRN settings on the [Qwen3.8-Flash-Next model card](https://huggingface.co/Qwen/Qwen3.8-Flash-Next). ### Optional MTP decoding The checkpoint includes the base model's one-layer MTP head. To enable self-speculative decoding, append the corresponding flags to the server command above: ~~~bash # vLLM --speculative-config '{"method":"mtp","num_speculative_tokens":1}' # SGLang --speculative-algorithm NEXTN --speculative-num-steps 3 \ --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 ~~~ The benchmark scores above were measured without MTP. ## License and access Swift 1.5 Qwen3.8-Flash-Next is a derivative of [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) (Copyright (c) 2026 Qwen, [Qwen Community License 1.0](https://huggingface.co/ukisai/Swift-Qwen3.8-Flash-Next/blob/main/LICENSE-QWEN)). UkisAI's contribution, including the adapted weights, is licensed under the **[Swift Open License v1.0](https://huggingface.co/ukisai/Swift-Qwen3.8-Flash-Next/blob/main/LICENSE)**. See [NOTICE](https://huggingface.co/ukisai/Swift-Qwen3.8-Flash-Next/blob/main/NOTICE) for the change notice and attribution details. Personal, research, educational, evaluation, and commercial use of the Swift contribution 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 [UkisAI](https://ukisai.com/contact) for terms. The base model's terms still apply to it. Under the Qwen Community License 1.0, organizations that run a Model-as-a-Service or AI Work Assistant business need a separate license from Qwen before any commercial use, and products above 100 million monthly active users or US$20 million monthly revenue must prominently display the model name. Nothing in the Swift Open License limits your rights in Qwen3.8-Flash-Next itself under the Qwen Community License. ## Citation ~~~bibtex @misc{swift-qwen3.8-flash-next, title = {Swift 1.5 Qwen3.8-Flash-Next}, author = {UkisAI}, year = {2026}, url = {https://huggingface.co/ukisai/Swift-Qwen3.8-Flash-Next} } ~~~ ## Acknowledgements We acknowledge the [NVIDIA Innovation Lab](https://www.nvidia.com/en-us/data-center/innovation-lab/), [Amazon Web Services](https://aws.amazon.com/), and [Google Cloud](https://cloud.google.com/) for providing compute credits and infrastructure support for Swift's development, training, and evaluation.