Instructions to use beyoru/Kiwen1.2-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beyoru/Kiwen1.2-27B with Transformers:

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

pipe = pipeline("image-text-to-text", model="beyoru/Kiwen1.2-27B")
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("beyoru/Kiwen1.2-27B")
model = AutoModelForMultimodalLM.from_pretrained("beyoru/Kiwen1.2-27B", device_map="auto")
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 beyoru/Kiwen1.2-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beyoru/Kiwen1.2-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/Kiwen1.2-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/beyoru/Kiwen1.2-27B

SGLang

How to use beyoru/Kiwen1.2-27B 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 "beyoru/Kiwen1.2-27B" \
    --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": "beyoru/Kiwen1.2-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "beyoru/Kiwen1.2-27B" \
        --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": "beyoru/Kiwen1.2-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use beyoru/Kiwen1.2-27B with Docker Model Runner:
```
docker model run hf.co/beyoru/Kiwen1.2-27B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Kiwen1.2-27B

Kiwen1.2 is a fine-tuned version of Qwen3.8-27B, trained on long chain-of-thought reasoning traces from Kimi K3 — with a particular focus on reasoning, coding, tool use, and instruction following. But the goal wasn't simply to make the model think longer. The goal was to make it think better.

This model isn't an attempt to build the biggest model.

It's an attempt to make a 27-billion-parameter model think harder, follow instructions better, and act more reliably.

News

RL in internal workflow by RLVR

Internal benchmark

Rank	Model	Pass Rate	Partial Rate
1	`Kiwen1.2`	81.2%	89.62%
2	`gemini-3.7-flash`	81.0%	89.8%
3	`gemini-3.6-flash`	80.0%	88.9%
4	`Kiwen1.1`	78.1%	87.85%

the benchmark includes 100 internal tasks for agent workflow

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

m = "beyoru/Kiwen1.1-27B"
tok = AutoTokenizer.from_pretrained(m)
model = AutoModelForCausalLM.from_pretrained(m, dtype="auto", device_map="auto")

msgs = [{"role": "user", "content": "Natalia sold clips to 48 friends in April, "
                                     "and half as many in May. How many total?"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True,
                              enable_thinking=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(ids, max_new_tokens=4096)[0][ids.shape[-1]:]))

Set enable_thinking=False for extraction, classification and formatting tasks. The model was trained with both modes and respects the flag.

Serving with SGLang:

python -m sglang.launch_server --model-path beyoru/Kiwen1.2-27B \
  --context-length 262144

Notes:

Found some issues in response quality when using with dflash2 - make sure you don't use this model with it
Found some loop issues in the previous version for long agentic task - ask hope this version can fix when it train for nearly long horizon task as least
Just little improvement in GSM8K and ifeval so the benchmark is not show above instead the benchmark in internal workflow is become better and model do more efficient steps

Citation

@misc{kiwen27bk3,
  title  = {Kiwen1.2-27B},
  author = {beyoru},
  year   = {2026},
  url    = {https://huggingface.co/beyoru/Kiwen1.2-27B}
}

License & Attribution

Built on:

Qwen3.8-27B — Apache-2.0

Kiwen1.2-27B is released under the Apache-2.0 license.

Downloads last month: 90

Safetensors

Model size

28B params

Tensor type

BF16

Model tree for beyoru/Kiwen1.2-27B

Base model

Qwen/Qwen3.8-27B

Finetuned

beyoru/Kiwen1.1-27B

Finetuned

(1)

this model

Quantizations

3 models