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

Kimi Dev 72B by moonshotai

 »  All LLMs  »  moonshotai  »  Kimi Dev 72B   URL Share it on

  6066   
  Autotrain compatible Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2.5-72b   Code   Conversational   Endpoints compatible   Issue-resolving   Qwen2   Region:us   Safetensors   Sharded   Software   Swebench   Tensorflow
Model Card on HF 🤗: https://huggingface.co/moonshotai/Kimi-Dev-72B 

Kimi Dev 72B Benchmarks

LLME Score: 0.37089
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kimi Dev 72B (moonshotai/Kimi-Dev-72B)
🌟 Advertise your project 🚀

Kimi Dev 72B Parameters and Internals

LLM NameKimi Dev 72B
Repository 🤗https://huggingface.co/moonshotai/Kimi-Dev-72B 
Base Model(s)  Qwen/Qwen2.5-72B   Qwen/Qwen2.5-72B
Model Size72b
Required VRAM83.4 GB
Updated2025-09-23
Maintainermoonshotai
Model Typeqwen2
Model Files  4.2 GB: 1-of-80   1.8 GB: 10-of-80   1.8 GB: 11-of-80   1.8 GB: 12-of-80   1.8 GB: 13-of-80   1.8 GB: 14-of-80   1.8 GB: 15-of-80   1.8 GB: 16-of-80   1.8 GB: 17-of-80   1.8 GB: 18-of-80   1.8 GB: 19-of-80   1.8 GB: 2-of-80   1.8 GB: 20-of-80   1.8 GB: 21-of-80   1.8 GB: 22-of-80   1.8 GB: 23-of-80   1.8 GB: 24-of-80   1.8 GB: 25-of-80   1.8 GB: 26-of-80   1.8 GB: 27-of-80   1.8 GB: 28-of-80   1.8 GB: 29-of-80   1.8 GB: 3-of-80   1.8 GB: 30-of-80   1.8 GB: 31-of-80   1.8 GB: 32-of-80   1.8 GB: 33-of-80   1.8 GB: 34-of-80   1.8 GB: 35-of-80   1.8 GB: 36-of-80   1.8 GB: 37-of-80   1.8 GB: 38-of-80   1.8 GB: 39-of-80   1.8 GB: 4-of-80   1.8 GB: 40-of-80   1.8 GB: 41-of-80   1.8 GB: 42-of-80   1.8 GB: 43-of-80   1.8 GB: 44-of-80   1.8 GB: 45-of-80   1.8 GB: 46-of-80   1.8 GB: 47-of-80   1.8 GB: 48-of-80   1.8 GB: 49-of-80   1.8 GB: 5-of-80
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Vocabulary Size152064
Torch Data Typebfloat16

Quantized Models of the Kimi Dev 72B

Model
Likes
Downloads
VRAM
Kimi Dev 72B 4bit DWQ18176440 GB
Kimi Dev 72B GPTQ 4bit2278145 GB
Kimi Dev 72B 8bit2109077 GB
Kimi Dev 72B 5bit36750 GB

Best Alternatives to Kimi Dev 72B

Best Alternatives
Context / RAM
Downloads
Likes
...R10528DistillQwen 72B Preview3195K / 146 GB156
Qwen2.5 72B128K / 145.5 GB3042478
Ultiima 72B128K / 146.1 GB743
Homer V1.0 Qwen2.5 72B128K / 146.1 GB1266
Ultiima 72B V1.5128K / 146.1 GB240
AceInstruct 72B128K / 146 GB21217
EVA Qwen2.5 72B V0.2128K / 146 GB18722
Qwen2 72B128K / 145.5 GB11962199
...n2.5 72B 2x Instruct TIES V1.0128K / 146.1 GB61
Dolphin 2.9.2 Qwen2 72B128K / 146 GB1515162

Rank the Kimi Dev 72B 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? 51535 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