Kimi-VL-Thinking

[!Warning] This model has a new version: Kimi-VL-A3B-Thinking-2506. Please consider using the new 2506 version for better abilties on general visual understanding, reasoning, video and agent scenarios.

Please set a higher temperature for thinking model, especially when your problem requires relatively long thinking process. We have updated the following sample script for HF inference.

1. Introduction

We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities—all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B).

Kimi-VL demonstrates strong performance across challenging domains: as a general-purpose VLM, Kimi-VL excels in multi-turn agent interaction tasks (e.g.,OSWorld), achieving state-of-the-art results comparable to flagship models. Furthermore, it exhibits remarkable capabilities across diverse challenging vision language tasks, including college-level image and video comprehension, optical character recognition (OCR), mathematical reasoning, multi-image understanding, and etc.

In comparative evaluations, it effectively competes with cutting-edge efficient VLMs such as GPT-4o-mini, Qwen2.5-VL-7B, and Gemma-3-12B-IT, while surpassing GPT-4o in several specialized domains.

Kimi-VL also advances the pareto frontiers of multimodal models in processing long contexts and perceiving clearly: Equipped with a 128K extended context window, Kimi-VL can processes long and diverse inputs, achieving impressive scores of 64.5 on LongVideoBench, and 35.1 on MMLongBench-Doc; Its native-resolution vision encoder, MoonViT, further allows it to see and understand ultra-high-resolution visual inputs, achieving 83.2 on InfoVQA and 34.5 on ScreenSpot-Pro, while maintaining lower computational cost with common visual inputs and general tasks.

Building on this foundation, we introduce an advanced long-thinking variant: Kimi-VL-Thinking. Developed through long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL), this model exhibits strong long-horizon reasoning capabilities. It achieves scores of 61.7 on MMMU, 36.8 on MathVision, and 71.3 on MathVista while maintaining the compact 2.8B activated LLM parameter footprint, setting a new standard for efficient yet capable multimodal thinking models.

More information can be found in our technical report: Kimi-VL Technical Report.

2. Architecture

The model adopts an MoE language model, a native-resolution visual encoder (MoonViT), and an MLP projector, as illustrated in the following image.

3. Model Variants

🤗 For general multimodal perception and understanding, OCR, long video and long document, video perception, and agent uses, we recommend Kimi-VL-A3B-Instruct for efficient inference; for advanced text and multimodal reasoning (e.g. math), please consider using Kimi-VL-A3B-Thinking.

[!Note] Recommended parameter settings:

• For Thinking models, it is recommended to use Temperature = 0.8.
• For Instruct models, it is recommended to use Temperature = 0.2.

4. Performance

With effective long-thinking abilitites, Kimi-VL-A3B-Thinking can match the performance of 30B/70B frontier open-source VLMs on MathVision benchmark:

Full comparison on MMMU, MathVision, and MathVista-mini:

Inference with 🤗 Hugging Face Transformers

We introduce how to use our model at inference stage using transformers library. It is recommended to use python=3.10, torch>=2.1.0, and transformers=4.48.2 as the development environment.

from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor

model_path = "moonshotai/Kimi-VL-A3B-Thinking"
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)

image_paths = ["./figures/demo1.png", "./figures/demo2.png"]
images = [Image.open(path) for path in image_paths]
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image_path} for image_path in image_paths
        ] + [{"type": "text", "text": "Please infer step by step who this manuscript belongs to and what it records"}],
    },