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

DeepSeek V2.5 1210 3bit by mlx-community

 »  All LLMs  »  mlx-community  »  DeepSeek V2.5 1210 3bit   URL Share it on

  46   
  3-bit   3bit   Autotrain compatible Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Conversational   Custom code   Deepseek v2   Endpoints compatible   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepSeek-V2.5-1210-3bit 

DeepSeek V2.5 1210 3bit Benchmarks

LLME Score: 0.28037
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek V2.5 1210 3bit (mlx-community/DeepSeek-V2.5-1210-3bit)

DeepSeek V2.5 1210 3bit Parameters and Internals

LLM NameDeepSeek V2.5 1210 3bit
Repository 🤗https://huggingface.co/mlx-community/DeepSeek-V2.5-1210-3bit 
Base Model(s)  deepseek-ai/DeepSeek-V2.5-1210   deepseek-ai/DeepSeek-V2.5-1210
Model Size29.5b
Required VRAM102.9 GB
Updated2024-12-22
Maintainermlx-community
Model Typedeepseek_v2
Model Files  5.0 GB: 1-of-20   5.2 GB: 2-of-20   5.2 GB: 3-of-20   5.2 GB: 4-of-20   5.2 GB: 5-of-20   5.2 GB: 6-of-20   5.2 GB: 7-of-20   5.2 GB: 8-of-20   5.2 GB: 9-of-20   5.2 GB: 10-of-20   5.2 GB: 11-of-20   5.2 GB: 12-of-20   5.2 GB: 13-of-20   5.2 GB: 14-of-20   5.2 GB: 15-of-20   5.2 GB: 16-of-20   5.2 GB: 17-of-20   5.2 GB: 18-of-20   5.2 GB: 19-of-20   4.3 GB: 20-of-20
Quantization Type3bit
Model ArchitectureDeepseekV2ForCausalLM
Licenseother
Context Length163840
Model Max Length163840
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size102400
Torch Data Typebfloat16

Rank the DeepSeek V2.5 1210 3bit 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? 40066 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 v20241217
  Support LLM Explorer