What are the hardware requirements for R1 1776?

R1 1776 requires approximately 243.4 GB of VRAM and supports a context window of 160K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed R1 1776 and how large is it?

R1 1776 is developed by perplexity-ai, a model with 671b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate R1 1776?

R1 1776 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

R1 1776 by perplexity-ai — VRAM 243.4GB, 160K context

Name: R1 1776
Author: perplexity-ai

R1 1776 is an open-source language model by perplexity-ai. Features: 671b LLM, VRAM: 243.4GB, Context: 160K, License: mit, LLM Explorer Score: 0.24.

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 Parameters and Internals

LLM Name	R1 1776
Repository 🤗	https://huggingface.co/perplexity-ai/r1-1776
Base Model(s)	DeepSeek R1 deepseek-ai/DeepSeek-R1
Model Size	671b
Required VRAM	243.4 GB
Updated	2025-11-10
Maintainer	perplexity-ai
Model Type	deepseek_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 Architecture	DeepseekV3ForCausalLM
License	mit
Context Length	163840
Model Max Length	163840
Transformers Version	4.46.3
Vocabulary Size	129280
Torch Data Type	bfloat16

Rank the R1 1776 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Quantized Models of the R1 1776

Model	Likes	Downloads	VRAM
R1 1776 GGUF	103	1064	0 GB

Best Alternatives to R1 1776

Best Alternatives	Context / RAM	Downloads	Likes
DeepSeek Prover V2 671B	160K / 189 GB	562	831
Cogito 671B V2.1	160K / 219.9 GB	85	29
Deepseek V3.1 MLX 5.5bit	160K / 231 GB	339	5
MAI DS R1	160K / 171.7 GB	333	306
...o V2 Preview Deepseek 671B MoE	160K / 219.9 GB	118	37
DeepSeek Prover V2 671B	160K / 184.7 GB	9	3
DeepSeek V3.1 Terminus 4bit	160K / 190.1 GB	42	2
DeepSeek V3.1 8bit	160K / 177.8 GB	4268	3
RakutenAI 3.0 MLX 4bit	160K / 198.7 GB	28	2
DeepSeek V3.1 4bit	160K / 190.1 GB	2974	6

Note: green Score (e.g. "73.2") means that the model is better than perplexity-ai/r1-1776.