Instructions to use ginigen-ai/Rogue-27B-KR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ginigen-ai/Rogue-27B-KR with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ginigen-ai/Rogue-27B-KR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ginigen-ai/Rogue-27B-KR", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ginigen-ai/Rogue-27B-KR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ginigen-ai/Rogue-27B-KR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ginigen-ai/Rogue-27B-KR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ginigen-ai/Rogue-27B-KR

SGLang

How to use ginigen-ai/Rogue-27B-KR with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ginigen-ai/Rogue-27B-KR" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ginigen-ai/Rogue-27B-KR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ginigen-ai/Rogue-27B-KR" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ginigen-ai/Rogue-27B-KR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ginigen-ai/Rogue-27B-KR with Docker Model Runner:
```
docker model run hf.co/ginigen-ai/Rogue-27B-KR
```

Rogue-27B-KR — Korean-Specialized High-Performance Reasoning Model

Qwen3.5 Hybrid Architecture | ~26B Params | Thinking Mode | 262K Context | BF16 | Apache 2.0 Darwin-27B-Opus(Father) + Korean-SFT Qwen 27B(Mother) Merge + Korean SFT

K-AI Leaderboard — 2nd Place

K-AI Leaderboard is operated by the Korean Ministry of Science and ICT (MSIT) / NIA, evaluating Korean AI language models across multiple benchmarks.

Rogue-27B-KR achieved 2nd place on the K-AI Leaderboard with an average score of 0.549.

K-AI Leaderboard Ranking

Metric	Score
Average	0.549
KMMLU-Pro	0.658
CLIcK	0.794
HLE(Ko)	0.07
MuSR(Ko)	0.584
Com2-main(Ko)	0.646

K-AI Leaderboard Charts

Model Overview

Rogue-27B-KR is a Korean-specialized high-performance reasoning model:

Father: FINAL-Bench/Darwin-27B-Opus — Evolutionary merge model based on Qwen3.5-27B (inheriting Claude 4.6 Opus reasoning patterns)
Mother: Korean-specialized SFT applied Qwen 27B variant
Rogue: Merged both parents + additional Korean SFT

Combines Darwin's powerful reasoning with the mother model's Korean expressiveness, greatly enhancing Korean intelligence across culture, language, law, history, and more.

Key Features

K-AI Leaderboard 2nd Place — Top-tier Korean AI performance verified by government evaluation
Strong reasoning — Chain-of-Thought inherited from Darwin-27B-Opus
Enhanced Korean cultural intelligence — +6%p improvement on CLIcK benchmark (0.794)
262K context — Ultra-long Korean document processing
Thinking mode — Step-by-step reasoning via <think> tags
BF16 format — Memory-efficient (~48GB), optimized for modern GPUs
Apache 2.0 — Free for commercial use

Benchmark Results

CLIcK (Cultural and Linguistic Intelligence in Korean)

200 questions, 0-shot evaluation:

Model	CLIcK (Overall)	Culture	Language
Qwen3.5-27B (base)	69.52%	71.84%	64.66%
Darwin-27B-Opus	70.19%	72.91%	64.47%
Rogue-27B-KR	75.59%	77.85%	70.86%

+6.07%p over Qwen3.5-27B, +5.40%p over Darwin-27B-Opus

Category Details

Category	Qwen3.5-27B	Darwin-27B-Opus	Rogue-27B-KR
Economy	93.22%	93.22%	94.92%
Geography	70.23%	70.23%	75.57%
History	47.00%	47.00%	53.50%
K-pop	92.68%	97.56%	92.68%
Law	59.50%	60.00%	69.50%
Politics	80.95%	82.14%	85.71%
Society	87.00%	89.00%	90.00%
Tradition	81.50%	82.50%	88.50%
Function Words	68.18%	67.42%	75.00%
Grammar	44.50%	44.50%	53.00%
Text	82.50%	82.50%	86.00%

Model Specifications

Property	Value
Architecture	Qwen3.5 (GatedDeltaNet Hybrid Attention, 64-layer)
Parameters	~26B (text-only, no vision encoder)
Hidden Size	5120
Intermediate Size	16384
Layers	64
Attention Heads	24 (GQA, KV Heads: 4)
Context Length	262,144 tokens (1M with YaRN)
Precision	BF16 (~48GB)
Vocab Size	248,320
Thinking	Supported (`<think>` tags)
Languages	Korean, English, Japanese, Chinese + 201 languages
License	Apache 2.0

VRAM Requirements

Setup	VRAM	Notes
BF16 (native)	~48 GB	Single H100/B200 or 2x A100
4-bit quantized	~14 GB	Single RTX 4090
8-bit quantized	~26 GB	Single A6000

Usage

Requirements: transformers >= 4.57.0 (Qwen3.5 support). Latest recommended: pip install -U transformers

Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("ginigen-ai/Rogue-27B-KR")
model = AutoModelForCausalLM.from_pretrained(
    "ginigen-ai/Rogue-27B-KR",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [{"role": "user", "content": "Explain traditional Korean wedding ceremonies."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=4096, do_sample=False)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

vLLM

vllm serve ginigen-ai/Rogue-27B-KR \
    --enforce-eager \
    --max-model-len 32768 \
    --dtype bfloat16

SGLang

python -m sglang.launch_server \
    --model-path ginigen-ai/Rogue-27B-KR \
    --tp 1 \
    --mem-fraction-static 0.90 \
    --context-length 32768 \
    --dtype bfloat16 \
    --reasoning-parser qwen3

Training Info

Item	Details
Father model	FINAL-Bench/Darwin-27B-Opus — Reasoning
Mother model	Korean-SFT Qwen 27B variant — Korean expressiveness
Merge	Weight merge (intermediate_size 16384 adopted)
Additional SFT	Korean-specialized Supervised Fine-Tuning
Developer	GinigenAI

Lineage

Qwen/Qwen3.5-27B (Apache 2.0)
+-- FINAL-Bench/Darwin-27B-Opus (evolutionary merge)  <- Father
|
+-- Korean-SFT Qwen 27B (Korean specialization)       <- Mother
        |
    [Merge: Father + Mother]
        |
    [Additional Korean SFT]
        |
    ginigen-ai/Rogue-27B-KR (this model, BF16)

Citation

@misc{ginigen_rogue_27b_kr_2026,
  title        = {Rogue-27B-KR: Korean-Specialized High-Performance Reasoning Model},
  author       = {GinigenAI},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ginigen-ai/Rogue-27B-KR}}
}

Acknowledgements

VIDRAFT — Darwin-27B-Opus base model
Qwen Team — Qwen3.5 architecture
Korean Ministry of Science and ICT / NIA — K-AI Leaderboard

Built by GinigenAI for the Korean AI community

학습 데이터셋

본 모델은 AI Hub(과학기술정보통신부·NIA 구축) 공개 한국어 말뭉치로 파인튜닝되었습니다.

✅ 전문 의학지식 데이터 ✅ 한국어 생성 기반 상식추론 데이터셋 ✅ 금융·법률 문서 기계독해 데이터 ✅ 국가기록물 초거대 AI 학습 말뭉치 ✅ 대규모 구매도서 기반 한국어 말뭉치 ✅ 멀티세션·대화 관련 말뭉치 데이터 ✅ 한국어 대화 데이터셋

Downloads last month: 15

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for ginigen-ai/Rogue-27B-KR

FINAL-Bench/Darwin-27B-Opus

Qwen/Qwen3.5-27B

Merge model

this model