Swift-Qwen3.8-27b EXL3 4.00bpw HB8

This repository contains an EXL3 quantization of ukisai/Swift-Qwen3.8-27b for ExLlamaV3.

Quantization

Model: ukisai/Swift-Qwen3.8-27b
Quantizer: exllamav3-1.4.4
Format: exl3
Bits per weight: 4.00
Head bits: 8
Calibration: 250 rows, 2048 columns
Output scales: always
Codebook: mul1
Files: 2 sharded .safetensors files

Compatibility

For the original model card and non-quantized weights, see ukisai/Swift-Qwen3.8-27b.

Original Model Card: Swift-Qwen3.8-27b

Website • Learn more • GGUF • Enterprise licensing

Swift-Qwen3.8-27B

Swift-Qwen3.8-27B is UkisAI's reasoning-efficient derivative of Qwen3.8-27B, using 58.3% fewer thinking tokens while maintaining near-identical performance (<1% loss) and as a result getting a x1.95 speed-up on several tasks.

The prompt is a sample from LiveCodeBench v6

Training approach

We built Swift by identifying reasoning-marker tokens that, in our analysis, trigger overthinking in Qwen’s reasoning rollouts. We then fine-tuned Qwen by penalizing usage of those tokens while it reasons.

Swift produces shorter reasoning traces. In our testing, we also observe fewer overthinking errors.

For maximum gains, Swift also includes a transfer component derived from BottleCap AI's ThinkingCap-Qwen3.6-27B.

Evaluation scope

All results below compare the Qwen3.8-27B BF16 base with the same base plus the Swift adapter.

Benchmarks

Benchmark	Score		Mean tokens			Median tokens
Benchmark	Base	Swift	Base	Swift	Reduction	Reduction
General reasoning
GPQA-Diamond	88.38%	88.28%	15,014	8,855	↓ 41.0%	↓ 58.3%
MMLU-Pro	85.47%	84.95%	2,980	1,603	↓ 46.2%	↓ 28.3%
C-Eval	90.00%	90.62%	1,492	804	↓ 46.1%	↓ 19.3%
IFBench	73.53%	71.80%	8,052	4,657	↓ 42.2%	↓ 50.5%
Mathematics
AIME 2026	98.67%	94.00%	22,014	16,143	↓ 26.7%	↓ 50.2%
HMMT (Nov 2025)	99.33%	96.00%	22,032	15,189	↓ 31.1%	↓ 45.9%
Multimodal
ERQA	67.45%	66.30%	4,137	2,045	↓ 50.6%	↓ 54.6%
Agentic coding
Terminal-Bench 2.1	66.74%	65.84%	37,086	27,272	↓ 26.5%	↓ 38.7%
LiveCodeBench v6	76.76%	81.55%	11,374	8,615	↓ 24.3%	↓ 45.8%

How to reproduce

Serving: BF16 · vLLM 0.27.1 · Qwen3 parser · context 262,144 · thinking xhigh.
Sampling: temperature 1.0 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 0 · repetition_penalty 1.
Benchmarks: averages over five seeds (0–4) per model; five trials per task for Terminal-Bench.

Benchmark	Output cap
GPQA-Diamond	100,000
MMLU-Pro	100,000
C-Eval	16,384
IFBench	81,920
AIME 2026	250,000
HMMT Nov 2025	250,000
ERQA	100,000
Terminal-Bench 2.1	Agent/task limits
LiveCodeBench v6	32,768

Efficiency across and versus reasoning efforts

Qwen3.8's reasoning_effort setting lets users choose how much the model thinks. For Swift to be useful across these settings, it needs to reduce thinking while keeping accuracy close to the base. We therefore tested xhigh, medium, and low: thinking-token savings persist at every level.

Reasoning effort	Mean thinking reduction
Xhigh	↓ 41.0%
Medium	↓ 22.7%
Low	↓ 25.8%

The efficiency also holds up against the base's own lower effort settings. On GPQA-Diamond (198 questions, 5 seeds, 990 paired calls), Swift at xhigh is compared with the base at xhigh and at medium:

GPQA-Diamond	Score	Mean tokens	Median tokens
Base · xhigh	88.38%	15,014	6,642
Swift · xhigh	88.28%	8,855	2,771
Base · medium	84.14%	4,451	1,753

Swift retains the accuracy of xhigh while using about half the tokens, although it uses about double the tokens of medium.

Quantized models

Quantized deployment is the intended use for Swift: lower-memory weights paired with shorter reasoning. The INT4 evaluations below retain token savings across GPQA, IFBench, and AIME. On AIME, Swift matches or improves accuracy and reduces output-cap failures by 31–33%.

Benchmark / quantization	Base accuracy	Swift accuracy	Mean token reduction	Median token reduction
GPQA-Diamond Mixed-precision quant W4A16 · thinking tokens	88.69%	88.38%	↓ 32.1%	↓ 50.2%
IFBench Mixed-precision quant W4A16 · completion tokens	72.58%	71.25%	↓ 30.1%	↓ 38.0%
AIME 2026 Mixed-precision quant W4A16 · completion tokens	84.00%	84.00%	↓ 19.0%	↓ 37.5%
AIME 2026 AWQ INT4 · completion tokens	82.67%	84.00%	↓ 22.8%	↓ 34.8%

Quantized evaluation settings

Each row compares the same quantized base with and without the Swift adapter. GPQA and AIME use five seeds; IFBench uses four samples per prompt and strict scoring. Output caps: GPQA 100,000; IFBench 81,920; AIME 32,768. GPQA and IFBench use saved historical base runs. AIME uses template-default effort and counts truncated answers as incorrect. Its shorter cap makes it a separate comparison from the BF16 table.

How to use

GGUF download

The GGUF version is available for compatible llama.cpp-based runtime.

UkisAI API

Swift is served through an OpenAI-compatible API at https://ukisai.com/api/swift/v1. It is free for research purposes and needs no API key. The model id is swift.

from openai import OpenAI

client = OpenAI(base_url="https://ukisai.com/api/swift/v1", api_key="none")
response = client.chat.completions.create(
    model="swift",
    messages=[{"role": "user", "content": "Explain speculative decoding in two sentences."}],
)
print(response.choices[0].message.content)

curl https://ukisai.com/api/swift/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "swift", "messages": [{"role": "user", "content": "Hello, Swift."}]}'

Transformers

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "ukisai/Swift-Qwen3.8-27b"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

vLLM

vllm serve ukisai/Swift-Qwen3.8-27b \
  --dtype bfloat16 \
  --tensor-parallel-size 1 \
  --max-model-len 262144 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --port 8000

SGLang

Alternatively, use a current SGLang build with Qwen3.8 support:

python -m sglang.launch_server \
  --model-path ukisai/Swift-Qwen3.8-27b \
  --dtype bfloat16 \
  --tp-size 1 \
  --context-length 262144 \
  --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 and SGLang recipe for installation and hardware-specific settings.

Optional MTP decoding

The published weights include the base model's MTP head. To enable self-speculative decoding, append the corresponding flags to the server command above:

# vLLM
--speculative-config '{"method":"mtp","num_speculative_tokens":3}'

# SGLang
--speculative-algorithm EAGLE --speculative-num-steps 3 \
  --speculative-eagle-topk 1 --speculative-num-draft-tokens 4

License and access

Swift-Qwen3.8-27B is a derivative of Qwen3.8-27B (Copyright 2026 Alibaba Cloud, Apache License 2.0). UkisAI's contribution, the fine-tuned weights, is licensed under the Swift Open License v1.0. See NOTICE for exactly what was changed.

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 UkisAI for terms.

Nothing in the Swift Open License limits your rights in Qwen3.8-27B itself under Apache 2.0.

Citation

@misc{swift-qwen3.8-27b,
  title  = {Swift-Qwen3.8-27B},
  author = {UkisAI},
  year   = {2026},
  url    = {https://huggingface.co/ukisai/Swift-Qwen3.8-27b}
}

Acknowledgements

We acknowledge the NVIDIA Innovation Lab for providing access to 8× NVIDIA H100 GPUs to train Swift.

darkbit1001/ukisai-Swift-Qwen3.8-27b-EXL3-4.00bpw-HB8HQ