What are the hardware requirements for Alpaca 70B Reproduced Llama 3?

Alpaca 70B Reproduced Llama 3 requires approximately 141.7 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Alpaca 70B Reproduced Llama 3 and how large is it?

Alpaca 70B Reproduced Llama 3 is developed by PKU-Alignment, a model with 70b 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 Alpaca 70B Reproduced Llama 3?

Alpaca 70B Reproduced Llama 3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Alpaca 70B Reproduced Llama 3 by PKU-Alignment — VRAM 141.7GB, 8K context

Name: Alpaca 70B Reproduced Llama 3
Author: PKU-Alignment

Alpaca 70B Reproduced Llama 3 is an open-source language model by PKU-Alignment. Features: 70b LLM, VRAM: 141.7GB, Context: 8K, Instruction-Based, LLM Explorer Score: 0.14.

Alpaca Beaver Dataset:tatsu-lab/alpaca Deepspeed En Ift Instruct Instruction-following Llama Region:us Safe-rlhf Safetensors Sft Sharded Supervised-fine-tuning Tensorflow

Model Card on HF 🤗: https://huggingface.co/PKU-Alignment/alpaca-70b-reproduced-llama-3

Alpaca 70B Reproduced Llama 3 Parameters and Internals

LLM Name	Alpaca 70B Reproduced Llama 3
Repository 🤗	https://huggingface.co/PKU-Alignment/alpaca-70b-reproduced-llama-3
Model Size	70b
Required VRAM	141.7 GB
Updated	2026-08-01
Maintainer	PKU-Alignment
Model Type	llama
Instruction-Based	Yes
Model Files	8.9 GB: 1-of-17 8.9 GB: 2-of-17 8.6 GB: 3-of-17 8.6 GB: 4-of-17 8.6 GB: 5-of-17 8.6 GB: 6-of-17 8.6 GB: 7-of-17 8.6 GB: 8-of-17 8.6 GB: 9-of-17 8.6 GB: 10-of-17 8.6 GB: 11-of-17 8.6 GB: 12-of-17 8.6 GB: 13-of-17 8.6 GB: 14-of-17 8.6 GB: 15-of-17 8.6 GB: 16-of-17 3.5 GB: 17-of-17
Supported Languages	en
Model Architecture	LlamaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.42.4
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	128258
Torch Data Type	bfloat16

Rank the Alpaca 70B Reproduced Llama 3 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

Best Alternatives to Alpaca 70B Reproduced Llama 3

Best Alternatives	Context / RAM	Downloads	Likes
... Chat 1048K Chinese Llama3 70B	1024K / 141.9 GB	9069	5
... Chat 1048K Chinese Llama3 70B	1024K / 141.9 GB	7684	4
... 3 70B Instruct Gradient 1048K	1024K / 141.9 GB	22	122
Llama3 Function Calling 1048K	1024K / 141.9 GB	5	1
...a 3 70B Instruct Gradient 524K	512K / 141.9 GB	24	23
...a 3 70B Instruct Gradient 262K	256K / 141.9 GB	20	56
...ama 3 70B Arimas Story RP V2.0	256K / 141.1 GB	10	3
...ama 3 70B Arimas Story RP V1.6	256K / 141.2 GB	5	0
...ama 3 70B Arimas Story RP V1.5	256K / 141.2 GB	21	3
Llama 3.1 70B Instruct	128K / 141.9 GB	813492	938

Note: green Score (e.g. "73.2") means that the model is better than PKU-Alignment/alpaca-70b-reproduced-llama-3.