Multimodal model

Kimi K2.5

Kimi K2.5 is Moonshot’s native multimodal open model, trained on about 15T vision-text tokens to power advanced coding and visual reasoning and to orchestrate self-directed agent swarms with up to 100 sub-agents and 1,500 tool calls.

Type
Multimodal
Weights
Open
Downloads
317k
Likes
2.9k
Pipeline
image text to text
License
other

Model hub

moonshotai/Kimi-K2.5

Repo
moonshotai/Kimi-K2.5
Library
transformers
Access
Public
Technical tags and languages
transformers safetensors kimi_k25 feature-extraction compressed-tensors image-text-to-text conversational custom_code eval-results
Open on Hugging Face

Papers

1

Related tools

7

More from Moonshot AI

10

About Moonshot AI

1

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

Benchmark scores

2

How Kimi K2.5 ranks on tracked AI benchmarks. Click any benchmark to see its full leaderboard.

Tools using Kimi K2.5

35