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 Thinking by mlx-community

 »  All LLMs  »  mlx-community  »  Kimi K2 Thinking   URL Share it on

  13203   

Kimi K2 Thinking is an open-source language model by mlx-community. Features: 1026.4b LLM, VRAM: 158.2GB, Context: 256K, License: other, LLM Explorer Score: 0.3.

  4-bit Base model:moonshotai/kimi-k2-... Base model:quantized:moonshota...   Conversational   Custom code   Kimi k2   Mlx   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Kimi-K2-Thinking 

Kimi K2 Thinking Benchmarks

LLME Score: 0.30026
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kimi K2 Thinking (mlx-community/Kimi-K2-Thinking)
🌟 Advertise your project 🚀

Kimi K2 Thinking Parameters and Internals

LLM NameKimi K2 Thinking
Repository 🤗https://huggingface.co/mlx-community/Kimi-K2-Thinking 
Base Model(s)  moonshotai/Kimi-K2-Thinking   moonshotai/Kimi-K2-Thinking
Model Size1026.4b
Required VRAM158.2 GB
Updated2026-03-27
Maintainermlx-community
Model Typekimi_k2
Model Files  3.5 GB: 1-of-182   3.5 GB: 2-of-182   3.5 GB: 3-of-182   3.8 GB: 4-of-182   3.5 GB: 5-of-182   3.5 GB: 6-of-182   3.8 GB: 7-of-182   3.5 GB: 8-of-182   3.5 GB: 9-of-182   3.8 GB: 10-of-182   3.5 GB: 11-of-182   3.5 GB: 12-of-182   3.8 GB: 13-of-182   3.5 GB: 14-of-182   3.5 GB: 15-of-182   3.8 GB: 16-of-182   3.5 GB: 17-of-182   3.5 GB: 18-of-182   3.8 GB: 19-of-182   3.5 GB: 20-of-182   3.5 GB: 21-of-182   3.8 GB: 22-of-182   3.5 GB: 23-of-182   3.5 GB: 24-of-182   3.8 GB: 25-of-182   3.5 GB: 26-of-182   3.5 GB: 27-of-182   3.8 GB: 28-of-182   3.5 GB: 29-of-182   3.5 GB: 30-of-182   3.8 GB: 31-of-182   3.5 GB: 32-of-182   3.5 GB: 33-of-182   3.8 GB: 34-of-182   3.5 GB: 35-of-182   3.5 GB: 36-of-182   3.8 GB: 37-of-182   3.5 GB: 38-of-182   3.5 GB: 39-of-182   3.8 GB: 40-of-182   3.5 GB: 41-of-182   3.5 GB: 42-of-182   3.8 GB: 43-of-182   3.5 GB: 44-of-182
Model ArchitectureDeepseekV3ForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.51.3
Vocabulary Size163840
Torch Data Typebfloat16

Best Alternatives to Kimi K2 Thinking

Best Alternatives
Context / RAM
Downloads
Likes
...i K2 Instruct 0905 Mlx DQ3 K M256K / 207.8 GB4745
Kimi K2 Instruct 0905 BF16256K / 1399.1 GB933
Kimi K2 Thinking 4bit256K / 151.2 GB5159
Kimi K2 Instruct 4bit128K / 143.2 GB1159413

Rank the Kimi K2 Thinking 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? 52052 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 v20260327b
  Support LLM Explorer