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

DeepSeek R1 by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  DeepSeek R1   URL Share it on

  77   

DeepSeek R1 is an open-source language model by unsloth. Features: 684.5b LLM, VRAM: 358.8GB, Context: 160K, License: mit, LLM Explorer Score: 0.33, ELO: 1398.

  Arxiv:2501.12948 Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Custom code   Deepseek   Deepseek v3   En   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF ๐Ÿค—: https://huggingface.co/unsloth/DeepSeek-R1 

DeepSeek R1 Benchmarks

LMSys ELO: 1398 vs 1272 (so35)9.9%
LLME Score: 0.32595
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek R1 (unsloth/DeepSeek-R1)
๐ŸŒŸ Advertise your project ๐Ÿš€

DeepSeek R1 Parameters and Internals

LLM NameDeepSeek R1
Repository ๐Ÿค—https://huggingface.co/unsloth/DeepSeek-R1 
Base Model(s)  DeepSeek R1   deepseek-ai/DeepSeek-R1
Model Size684.5b
Required VRAM358.8 GB
Updated2026-03-29
Maintainerunsloth
Model Typedeepseek_v3
Model Files  8.6 GB: 1-of-163   8.6 GB: 2-of-163   8.6 GB: 3-of-163   8.6 GB: 4-of-163   8.6 GB: 5-of-163   8.7 GB: 6-of-163   8.6 GB: 7-of-163   8.6 GB: 8-of-163   8.6 GB: 9-of-163   8.6 GB: 10-of-163   8.6 GB: 11-of-163   2.6 GB: 12-of-163   8.6 GB: 13-of-163   8.6 GB: 14-of-163   8.6 GB: 15-of-163   8.6 GB: 16-of-163   8.6 GB: 17-of-163   8.6 GB: 18-of-163   8.6 GB: 19-of-163   8.6 GB: 20-of-163   8.6 GB: 21-of-163   8.6 GB: 22-of-163   8.6 GB: 23-of-163   8.6 GB: 24-of-163   8.6 GB: 25-of-163   8.6 GB: 26-of-163   8.6 GB: 27-of-163   8.6 GB: 28-of-163   8.6 GB: 29-of-163   8.6 GB: 30-of-163   8.6 GB: 31-of-163   8.6 GB: 32-of-163   8.6 GB: 33-of-163   3.5 GB: 34-of-163   8.6 GB: 35-of-163   8.6 GB: 36-of-163   8.6 GB: 37-of-163   8.6 GB: 38-of-163   8.6 GB: 39-of-163   8.6 GB: 40-of-163   8.6 GB: 41-of-163   8.6 GB: 42-of-163   8.6 GB: 43-of-163
Supported Languagesen
Model ArchitectureDeepseekV3ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.48.1
Tokenizer ClassLlamaTokenizerFast
Padding Token<๏ฝœโ–padโ–๏ฝœ>
Vocabulary Size129280
Torch Data Typebfloat16

Best Alternatives to DeepSeek R1

Best Alternatives
Context / RAM
Downloads
Likes
Kimi K2 Thinking NVFP4256K / 210 GB482029
Kimi K2 Thinking BF16256K / 220 GB866
Kimi K2 Thinking256K / 383.2 GB304
DeepSeek V3.1160K / 180.4 GB150107819
DeepSeek V3.1 Terminus160K / 171.8 GB11934
DeepSeek V3.1 Base160K / 180.4 GB106441010
DeepSeek V3.1160K / 176.1 GB443
DeepSeek V3.0324160K / 376 GB358
DeepSeek V3 Base160K / 171.8 GB23451684
DeepSeek R1 0528 FP4160K / 107 GB7299136
Note: green Score (e.g. "73.2") means that the model is better than unsloth/DeepSeek-R1.

Rank the DeepSeek R1 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 52334 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 โ€” our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer