Kimi-K2.5-Thinking-Eagle3

Model Overview

Description:

The NVIDIA Kimi-K2.5 Eagle model is the Eagle head of the Moonshot AI's Kimi-K2.5 model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Kimi-K2.5 Eagle3 model incorporates Eagle speculative decoding with Model Optimizer.

This model is ready for commercial/non-commercial use. <br>

License/Terms of Use:

Governing Terms: Use of this model is governed by the NVIDIA Open Model License. ADDITIONAL INFORMATION: Modified MIT License. Kimi-K2.5.

Deployment Geography:

Global

Use Case:

Developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. Also suitable for typical instruction-following tasks.

Release Date:

Hugging Face [03/10/2025] via [https://huggingface.co/nvidia/Kimi-K2.5-Eagle3]

Reference(s):

• Kimi K2.5: Visual Agentic Intelligence
• EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Model Architecture:

Architecture Type: Transformers <br> Network Architecture: DeepSeek V3 <br>
**This model was developed based on moonshotai/Kimi-K2.5.
** Number of model parameters 1.8*10^9

Input:

Input Type(s): Text <br> Input Format(s): String <br> Input Parameters: 1D (One Dimensional): Sequences <br> Other Properties Related to Input: Context length 4096

Output:

Output Type(s): Text <br> Output Format: String <br> Output Parameters: 1D (One Dimensional): Sequences <br> Other Properties Related to Output: None

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Software Integration:

Runtime Engine(s): <br>

• TensorRT-LLM <br>

Supported Hardware Microarchitecture Compatibility: <br>

• NVIDIA Blackwell <br>

Preferred Operating System(s): <br>

• Linux <br>

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version(s):

** The model (v1) is trained with nvidia-modelopt v0.42.0 <br>

Training and Evaluation Datasets:

** Total size (in number of data points) 112K. <br> ** Dataset partition: Training 100% <br>

Training Dataset:

Link: Nemotron-Post-Training-Dataset-v2, only prompts from the datasets were used for data synthesis, (the original responses from GPT were not used), which is then used to train the Eagle modules.

** Data Modality [Text]

** Text Training Data Size [Less than a Billion Tokens]

** Data Collection Method by dataset [Hybrid: Automated, Synthetic]

** Labeling Method by dataset [Hybrid: Automated, Synthetic]

Properties: 112K multilingual text samples featuring prompts spanning math, code, STEM, and conversational topics. Each sample includes a synthetic response generated by the target model.

Evaluation Dataset:

Link: MTBench, for more details, see here

** Data Collection Method by dataset

Hybrid: Human, Synthetic ** Labeling Method by dataset

Hybrid: Human, Synthetic Properties: 3,300 multi-turn dialogue sequences, each annotated with expert preference votes.

Inference:

Acceleration Engine: TensorRT-LLM <br> Test Hardware: B200 <br>

Eagle Speculative Decoding

Synthesized data was obtained from Moonshot AI's Kimi-K2.5 model, which is then used to finetune the Eagle modules. This model is ready for inference with TensorRT-LLM in Eagle speculative decoding mode. Eagle modules are used to predict candidate tokens beyond the next token. In the generation step, each forward Eagle module generates a distribution of tokens beyond the previous. The longest accepted candidate sequence is selected so that more than 1 token is returned in the generation step. The number of tokens generated in each step is called acceptance rate.

Usage

To serve the checkpoint with TensorRT-LLM, follow the sample commands below with the TensorRT-LLM GitHub repo:

trtllm-serve <Kimi-K2.5-NVFP4 checkpoint> --host 0.0.0.0 --port 8000 --backend pytorch --max_batch_size 32 --max_num_tokens 8192 --max_seq_len 8192 --tp_size 4 --extra_llm_api_options extra-llm-api-config.yml

with extra-llm-api-config.yml being

speculative_config:
    decoding_type: Eagle
    max_draft_len: 3
    speculative_model_dir: <eagle3 checkpoint>

Evaluation

The Eagle acceptance rate benchmark results (MT-Bench) with draft length 3 are presented in the table below for medium reasoning:

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards below.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

SUBCARDS:

Explainability

Bias

Safety & Security

Privacy