README.md

metadata

base_model:
  - LLM360/K2-V2-Instruct
language:
  - en
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation

K2-Think (70B): A Fully-Sovereign Reasoning System

📚 Paper - 📝 Code - 🏢 Project Page

K2-Think (70B) 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 system.

Quickstart

Serving configurations

We use the following serving configurations:

Setting	Value
Temperature	1.0
Top-p	1.0
Top-k	-1
Context Length	131072
Context Length Extension	2x using YaRN
Chat Template	Default provided in chat_template.jinja

The provided chat template sets the reasoning effort to high

Transformers

You can use K2-Think (70B) 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-70B"

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-70B",
    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 summary of evaluation results are reported in our Blog

Benchmarks (pass@1, average over 16 runs)

Domain	Benchmark	K2-Think (70B)
Math	AIME 2025	90.42
Math	HMMT 2025	84.79
Code	LiveCodeBench v5	TBD
Science	GPQA-Diamond	72.98
Science	Humanity's Last Exam	TBD

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 (70B) in your research, please use the following citation:

@misc{k2thinkteam2026k2think70B,
      title={K2-{T}hink 70{B}: A Fully-Sovereign Reasoning System}, 
      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://tbd.org}, 
}