What are the hardware requirements for Kimi K2 Thinking Eagle3?

Kimi K2 Thinking Eagle3 requires approximately 3.7 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kimi K2 Thinking Eagle3 and how large is it?

Kimi K2 Thinking Eagle3 is developed by nvidia, a model with 1.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Kimi K2 Thinking Eagle3?

Kimi K2 Thinking Eagle3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kimi K2 Thinking Eagle3 by nvidia — VRAM 3.7GB, 256K context

Name: Kimi K2 Thinking Eagle3
Author: nvidia

Kimi K2 Thinking Eagle3 is an open-source language model by nvidia. Features: 1.8b LLM, VRAM: 3.7GB, Context: 256K, License: other, LLM Explorer Score: 0.23.

Arxiv:2503.01840 Base model:finetune:moonshotai... Base model:moonshotai/kimi-k2-... Eagle3 Kimi-k2 Kimi k2 Model optimizer Modelopt Nvidia Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/nvidia/Kimi-K2-Thinking-Eagle3

Kimi K2 Thinking Eagle3 Parameters and Internals

LLM Name	Kimi K2 Thinking Eagle3
Repository 🤗	https://huggingface.co/nvidia/Kimi-K2-Thinking-Eagle3
Base Model(s)	Kimi K2 Thinking moonshotai/Kimi-K2-Thinking
Model Size	1.8b
Required VRAM	3.7 GB
Updated	2026-06-20
Maintainer	nvidia
Model Type	kimi_k2
Model Files	3.7 GB
Model Architecture	Eagle3DeepseekV2ForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	4.51.3
Vocabulary Size	163840
Torch Data Type	bfloat16

Rank the Kimi K2 Thinking Eagle3 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Kimi K2 Thinking Eagle3

Best Alternatives	Context / RAM	Downloads	Likes
Kimi K2.6 Eagle3	256K / 3.7 GB	11600	11
Kimi K2.5 Thinking Eagle3	256K / 3.7 GB	2080	17

Note: green Score (e.g. "73.2") means that the model is better than nvidia/Kimi-K2-Thinking-Eagle3.