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

R1 1776 by perplexity-ai

 »  All LLMs  »  perplexity-ai  »  R1 1776   URL Share it on

  10907   
  Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational   Custom code   Deepseek v3   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/perplexity-ai/r1-1776 

R1 1776 Benchmarks

LLME Score: 0.40513
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
R1 1776 (perplexity-ai/r1-1776)
🌟 Advertise your project 🚀

R1 1776 Parameters and Internals

LLM NameR1 1776
Repository 🤗https://huggingface.co/perplexity-ai/r1-1776 
Base Model(s)  DeepSeek R1   deepseek-ai/DeepSeek-R1
Model Size671b
Required VRAM243.4 GB
Updated2025-09-23
Maintainerperplexity-ai
Model Typedeepseek_v3
Model Files  5.2 GB: 1-of-252   5.2 GB: 2-of-252   5.2 GB: 3-of-252   5.2 GB: 4-of-252   5.3 GB: 5-of-252   5.3 GB: 6-of-252   5.3 GB: 7-of-252   5.3 GB: 8-of-252   5.3 GB: 9-of-252   5.3 GB: 10-of-252   5.3 GB: 11-of-252   5.3 GB: 12-of-252   5.3 GB: 13-of-252   5.3 GB: 14-of-252   5.3 GB: 15-of-252   5.3 GB: 16-of-252   5.3 GB: 17-of-252   5.3 GB: 18-of-252   5.3 GB: 19-of-252   5.3 GB: 20-of-252   5.3 GB: 21-of-252   5.3 GB: 22-of-252   5.3 GB: 23-of-252   5.3 GB: 24-of-252   5.3 GB: 25-of-252   5.3 GB: 26-of-252   5.3 GB: 27-of-252   5.3 GB: 28-of-252   5.3 GB: 29-of-252   5.3 GB: 30-of-252   5.3 GB: 31-of-252   5.3 GB: 32-of-252   5.3 GB: 33-of-252   5.3 GB: 34-of-252   5.3 GB: 35-of-252   5.3 GB: 36-of-252   5.3 GB: 37-of-252   5.3 GB: 38-of-252   5.3 GB: 39-of-252   5.3 GB: 40-of-252   5.3 GB: 41-of-252   5.3 GB: 42-of-252   5.3 GB: 43-of-252   5.3 GB: 44-of-252   5.3 GB: 45-of-252   5.3 GB: 46-of-252
Model ArchitectureDeepseekV3ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.46.3
Vocabulary Size129280
Torch Data Typebfloat16

Quantized Models of the R1 1776

Model
Likes
Downloads
VRAM
R1 1776 GGUF10215910 GB

Best Alternatives to R1 1776

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek Prover V2 671B160K / 189 GB1408809
MAI DS R1160K / 176 GB1158287
Deepseek V3.1 MLX 5.5bit160K / 231 GB23895
...o V2 Preview Deepseek 671B MoE160K / 219.9 GB7635
DeepSeek Prover V2 671B160K / 184.7 GB113
DeepSeek V3.1 8bit160K / 177.8 GB20883
DeepSeek V3.1 4bit160K / 190.1 GB16316
DeepSeek V3.1 Base 4bit160K / 190.1 GB18753
DeepSeek R1 0528 5bit160K / 231 GB1113
DeepSeek Prover V2 671B GGUF160K / 250 GB15398

Rank the R1 1776 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? 51544 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