K2-Think-V2

K2 Think V2: A Fully-Sovereign Reasoning Model

📚 Blog - 📝 Code - 🏢 Project Page

<center><img src="banner.png" alt="k2-think-banner"/></center> <br>

K2 Think V2 is a 70 billion parameter open-weights general reasoning model with strong performance in competitive mathematical problem solving built on-top of K2-V2-Instruct, comprising a fully sovereign reasoning model.

Quickstart

Serving configurations

We use the following serving configurations:

The provided chat template sets the reasoning effort to high

Serving commands

To serve on VLLM:

vllm serve LLM360/K2-Think-V2 --tensor-parallel-size 8 --port 8000

Transformers

You can use K2 Think V2 with Transformers. If you use transformers.pipeline, it will apply the chat template automatically. If you use model.generate directly, you need to apply the chat template mannually.

The chat template is directly inherited from K2-V2-Instruct, with the default reasoning_effort set to "high". The other levels of reasoning effort ("low" and "medium") are still available but have not been tested or evaluated. As such, the model's behavior under such settings is not assured to maintain reported performance.

from transformers import pipeline
import torch

model_id =  "LLM360/K2-Think-V2"

pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "what is the next prime number after 2600?"},
]

outputs = pipe(
    messages,
    max_new_tokens=131072,
)
print(outputs[0]["generated_text"][-1])

If you cannot use tokenizer.apply_chat_template, you may also pass in these arguments using extra_body and chat_template_kwargs:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="key"
)

completion = client.chat.completions.create(
    model="LLM360/K2-Think-V2",
    messages = [
        {"role": "system", "content": "You are K2-Think, a helpful assistant created by Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Institute of Foundation Models (IFM)."},
        {"role": "user", "content": "Solve the 24 game [2, 3, 5, 6]"}
    ],
    extra_body={
        "chat_template_kwargs": {"reasoning_effort": "high"},
    },
)

---

Evaluation & Performance

A more complete summary of evaluation results are reported in our Blog

Benchmarks (pass@1, average over 16 runs)

Safety Evaluation

Aggregated across four safety dimensions (Safety-4):

K2 Think V2 establishes a robust safety baseline while effectively resolving the "alignment tax" of previous K2 Think releases. Despite strong overall safety performance, there are still opportunities to improve the model with regard to handling sensitive personal information.

---

Terms of Use

We have employed various techniques to reduce bias, harmful outputs, and other risks in the model. While these efforts help improve safety and reliability, the model, like all Large Language Models, may still generate inaccurate, misleading, biased, or otherwise undesirable content. By downloading, using, or interacting with this model, you acknowledge these limitations and agree to the following:

1. Prohibited Uses

   • You may not use this model for any illegal, unlawful, or harmful activities, including but not limited to fraud, abuse, harassment, privacy violations, or the creation/dissemination of malicious content.

2. User Responsibility

   • You are solely responsible for how you use the model and for any outcomes that result from its use.
   • The authors and institutions involved in releasing this model do not accept liability for any consequences arising from its use.

3. No Warranty

   • The model is provided “as is” without any warranties or guarantees.

---

Citation

If you use K2 Think V2 in your research, please use the following citation:

@misc{k2think2026k2think0126,
      title={K2 {T}hink {V}2: A {F}ully-{S}overeign {R}easoning {M}odel}, 
      author={K2 Think Team and Taylor W. Killian and Varad Pimpalkhute and Richard Fan and Haonan Li and Chengqian Gao and Ming Shan Hee and Xudong Han and John Maggs and Guowei He and Zhengzhong Liu and Eric P. Xing},
      year={2026},
      url={https://mbzuai.ac.ae/news/k2-think-v2-a-fully-sovereign-reasoning-model}, 
}