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

Kimi K2 Instruct 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Kimi K2 Instruct 4bit   URL Share it on

  2993   
  4-bit   4bit Base model:moonshotai/kimi-k2-... Base model:quantized:moonshota...   Conversational   Custom code   Instruct   Kimi k2   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Kimi-K2-Instruct-4bit 

Kimi K2 Instruct 4bit Benchmarks

LLME Score: 0.29612
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kimi K2 Instruct 4bit (mlx-community/Kimi-K2-Instruct-4bit)
🌟 Advertise your project 🚀

Kimi K2 Instruct 4bit Parameters and Internals

LLM NameKimi K2 Instruct 4bit
Repository 🤗https://huggingface.co/mlx-community/Kimi-K2-Instruct-4bit 
Base Model(s)  Kimi K2 Instruct   moonshotai/Kimi-K2-Instruct
Model Size1026.4b
Required VRAM143.2 GB
Updated2025-09-09
Maintainermlx-community
Model Typekimi_k2
Instruction-BasedYes
Model Files  4.2 GB: 1-of-180   3.2 GB: 2-of-180   3.3 GB: 3-of-180   3.2 GB: 4-of-180   3.2 GB: 5-of-180   3.3 GB: 6-of-180   3.2 GB: 7-of-180   3.2 GB: 8-of-180   3.3 GB: 9-of-180   3.2 GB: 10-of-180   3.2 GB: 11-of-180   3.3 GB: 12-of-180   3.2 GB: 13-of-180   3.2 GB: 14-of-180   3.3 GB: 15-of-180   3.2 GB: 16-of-180   3.2 GB: 17-of-180   3.3 GB: 18-of-180   3.2 GB: 19-of-180   3.2 GB: 20-of-180   3.3 GB: 21-of-180   3.2 GB: 22-of-180   3.2 GB: 23-of-180   3.3 GB: 24-of-180   3.2 GB: 25-of-180   3.2 GB: 26-of-180   3.3 GB: 27-of-180   3.2 GB: 28-of-180   3.2 GB: 29-of-180   3.3 GB: 30-of-180   3.2 GB: 31-of-180   3.2 GB: 32-of-180   3.3 GB: 33-of-180   3.2 GB: 34-of-180   3.2 GB: 35-of-180   3.3 GB: 36-of-180   3.2 GB: 37-of-180   3.2 GB: 38-of-180   3.3 GB: 39-of-180   3.2 GB: 40-of-180   3.2 GB: 41-of-180   3.3 GB: 42-of-180   3.2 GB: 43-of-180   3.2 GB: 44-of-180
Quantization Type4bit
Model ArchitectureDeepseekV3ForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.48.3
Vocabulary Size163840
Torch Data Typebfloat16

Best Alternatives to Kimi K2 Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...i K2 Instruct 0905 Mlx DQ3 K M256K / 207.8 GB3194
Kimi K2 Instruct 0905 BF16256K / 1399.1 GB163
Kimi K2 Instruct BF16128K / 1367.3 GB3843
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Kimi-K2-Instruct-4bit.

Rank the Kimi K2 Instruct 4bit 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? 51221 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.
Release v20241124
  Support LLM Explorer