LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Kimi K2.5 by moonshotai

 »  All LLMs  »  moonshotai  »  Kimi K2.5   URL Share it on

  4471788   

Kimi K2.5 is an open-source language model by moonshotai. Features: 1058.6b LLM, VRAM: 344GB, License: other, LLM Explorer Score: 0.6.

  Arxiv:2602.02276   Compressed-tensors   Conversational   Custom code   Eval-results   Feature-extraction   Image-text-to-text   Kimi k25   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/moonshotai/Kimi-K2.5 

Kimi K2.5 Benchmarks

LLME Score: 0.5995
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kimi K2.5 (moonshotai/Kimi-K2.5)
🌟 Advertise your project 🚀

Kimi K2.5 Parameters and Internals

LLM NameKimi K2.5
Repository 🤗https://huggingface.co/moonshotai/Kimi-K2.5 
Model Size1058.6b
Required VRAM344 GB
Updated2026-03-28
Maintainermoonshotai
Model Typekimi_k25
Model Files  1.0 GB: 1-of-64   9.8 GB: 2-of-64   9.8 GB: 3-of-64   9.8 GB: 4-of-64   9.8 GB: 5-of-64   9.8 GB: 6-of-64   9.8 GB: 7-of-64   9.8 GB: 8-of-64   9.8 GB: 9-of-64   9.8 GB: 10-of-64   9.8 GB: 11-of-64   9.8 GB: 12-of-64   9.8 GB: 13-of-64   9.8 GB: 14-of-64   9.8 GB: 15-of-64   9.8 GB: 16-of-64   9.8 GB: 17-of-64   9.8 GB: 18-of-64   9.8 GB: 19-of-64   9.8 GB: 20-of-64   9.8 GB: 21-of-64   9.8 GB: 22-of-64   9.8 GB: 23-of-64   9.8 GB: 24-of-64   9.8 GB: 25-of-64   9.8 GB: 26-of-64   9.8 GB: 27-of-64   9.8 GB: 28-of-64   9.8 GB: 29-of-64   9.8 GB: 30-of-64   9.8 GB: 31-of-64   9.8 GB: 32-of-64   9.8 GB: 33-of-64   9.8 GB: 34-of-64   9.8 GB: 35-of-64   9.8 GB: 36-of-64
Model ArchitectureKimiK25ForConditionalGeneration
Licenseother

Quantized Models of the Kimi K2.5

Model
Likes
Downloads
VRAM
Kimi K2.5 Mlx DQ3 K M Q821395186 GB

Rank the Kimi K2.5 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 52221 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer