Multimodal model

Kimi K3

Kimi K3 is a 2.8 trillion parameter sparse Mixture-of-Experts language model with native vision understanding and a context window of up to 1 million tokens. It uses Kimi Delta Attention and Attention Residuals to improve long-context efficiency and depth scaling, with an always-on reasoning mode for coding, knowledge work, and agentic tool use.

Type
Multimodal
Weights
Open
Downloads
1.6M
Likes
12k
Pipeline
image text to text
License
other

Model hub

moonshotai/Kimi-K3

Repo
moonshotai/Kimi-K3
Library
transformers
Access
Public
Technical tags and languages
transformers safetensors kimi_k3 feature-extraction compressed-tensors conversational image-text-to-text custom_code eval-results 8-bit
Open on Hugging Face

Related tools

10

More from Moonshot AI

9

Pricing

1

About Moonshot AI

1

Moonshot AI is a Beijing-based Chinese AI startup (founded 2023) focused on developing large language models and multimodal systems

Tools using Kimi K3

40