Instructions to use websfactory/Webs-KoReasoner-27B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use websfactory/Webs-KoReasoner-27B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="websfactory/Webs-KoReasoner-27B-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("websfactory/Webs-KoReasoner-27B-v1")
model = AutoModelForMultimodalLM.from_pretrained("websfactory/Webs-KoReasoner-27B-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use websfactory/Webs-KoReasoner-27B-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/websfactory/Webs-KoReasoner-27B-v1

SGLang

How to use websfactory/Webs-KoReasoner-27B-v1 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 "websfactory/Webs-KoReasoner-27B-v1" \
    --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": "websfactory/Webs-KoReasoner-27B-v1",
		"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 "websfactory/Webs-KoReasoner-27B-v1" \
        --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": "websfactory/Webs-KoReasoner-27B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use websfactory/Webs-KoReasoner-27B-v1 with Docker Model Runner:
```
docker model run hf.co/websfactory/Webs-KoReasoner-27B-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Webs-KoReasoner-27B-v1

A same-base DARE-TIES soup of two strong open Korean-reasoning models, built on a single GPU-less Apple Mac mini (M4 Pro, 64GB) with a custom disk-streaming merger.

Recipe

Base: Qwen/Qwen3.5-27B (Apache-2.0)
Donors (same base):
- NewenAI/QuettaLLMs-27B-Koreasoner-V3
- jiwon9703/Qwen3.5-KoReasoin-27B-v1
Method: DARE-TIES (density 0.5, standard 1/density rescale, weight 1.0, seed 42), TIES sign-election across the two task vectors, applied to all tensors (including MLP). fp32 math, streamed one tensor at a time so a 64GB machine never holds more than one tensor's working set.

Because mergekit cannot express the Qwen3_5 hybrid architecture (interleaved linear_attention / full_attention layers), the merge was produced with an in-house streaming merger.

Intended use

Korean knowledge & reasoning. The model thinks (often in English) inside <think> … </think> and answers in Korean.

Credits

All weights derive from the Apache-2.0 base and donors above; full credit to their authors. Merge engineering by 웹스팩토리 (Websfactory).

Downloads last month: 50

Safetensors

Model size

28B params

Tensor type

BF16

F32

Model tree for websfactory/Webs-KoReasoner-27B-v1

NewenAI/QuettaLLMs-27B-Koreasoner-V3

Qwen/Qwen3.5-27B

jiwon9703/KoQweopus-3.5-27B-experimental

Merge model

this model

Quantizations

2 models