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 Instruct 0905 Mlx DQ3 K M by mlx-community

 »  All LLMs  »  mlx-community  »  Kimi K2 Instruct 0905 Mlx DQ3 K M   URL Share it on

  808   

Kimi K2 Instruct 0905 Mlx DQ3 K M is an open-source language model by mlx-community. Features: 1026.4b LLM, VRAM: 204.6GB, Context: 256K, License: other, Instruction-Based, LLM Explorer Score: 0.22.

  Arxiv:2505.02390   4-bit Base model:moonshotai/kimi-k2-... Base model:quantized:moonshota...   Conversational   Custom code   Instruct   Kimi k2   Mlx   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Kimi-K2-Instruct-0905-mlx-DQ3_K_M 

Kimi K2 Instruct 0905 Mlx DQ3 K M Benchmarks

LLME Score: 0.22204
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 0905 Mlx DQ3 K M (mlx-community/Kimi-K2-Instruct-0905-mlx-DQ3_K_M)
🌟 Advertise your project 🚀

Kimi K2 Instruct 0905 Mlx DQ3 K M Parameters and Internals

LLM NameKimi K2 Instruct 0905 Mlx DQ3 K M
Repository 🤗https://huggingface.co/mlx-community/Kimi-K2-Instruct-0905-mlx-DQ3_K_M 
Base Model(s)  Kimi K2 Instruct 0905   moonshotai/Kimi-K2-Instruct-0905
Model Size1026.4b
Required VRAM204.6 GB
Updated2026-06-22
Maintainermlx-community
Model Typekimi_k2
Instruction-BasedYes
Model Files  3.5 GB: 1-of-99   2.5 GB: 2-of-99   4.7 GB: 3-of-99   4.9 GB: 4-of-99   4.7 GB: 5-of-99   4.9 GB: 6-of-99   4.7 GB: 7-of-99   4.9 GB: 8-of-99   4.7 GB: 9-of-99   4.9 GB: 10-of-99   3.3 GB: 11-of-99   4.9 GB: 12-of-99   5.0 GB: 13-of-99   5.0 GB: 14-of-99   4.9 GB: 15-of-99   5.0 GB: 16-of-99   5.0 GB: 17-of-99   4.9 GB: 18-of-99   3.3 GB: 19-of-99   4.9 GB: 20-of-99   5.0 GB: 21-of-99   5.0 GB: 22-of-99   4.9 GB: 23-of-99   5.0 GB: 24-of-99   5.0 GB: 25-of-99   4.9 GB: 26-of-99   3.3 GB: 27-of-99   4.9 GB: 28-of-99   5.0 GB: 29-of-99   5.0 GB: 30-of-99   4.9 GB: 31-of-99   5.0 GB: 32-of-99   5.0 GB: 33-of-99   4.9 GB: 34-of-99   3.3 GB: 35-of-99   4.9 GB: 36-of-99   5.0 GB: 37-of-99   5.0 GB: 38-of-99   4.9 GB: 39-of-99   5.0 GB: 40-of-99   5.0 GB: 41-of-99   4.9 GB: 42-of-99   3.3 GB: 43-of-99   4.9 GB: 44-of-99
Model ArchitectureDeepseekV3ForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.51.3
Vocabulary Size163840
Torch Data Typebfloat16

Best Alternatives to Kimi K2 Instruct 0905 Mlx DQ3 K M

Best Alternatives
Context / RAM
Downloads
Likes
Kimi K2 Instruct 4bit128K / 143.2 GB702913
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Kimi-K2-Instruct-0905-mlx-DQ3_K_M.

Rank the Kimi K2 Instruct 0905 Mlx DQ3 K M 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? 54868 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