What are the hardware requirements for Meta Llama 3 70B?

Meta Llama 3 70B requires approximately 141.9 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 Meta Llama 3 70B and how large is it?

Meta Llama 3 70B is developed by meta-llama, a model with 70b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Meta Llama 3 70B perform on standard benchmarks?

Meta Llama 3 70B has the following published scores: MMLU 79.23. Compare against reference models on this page or on the LLM Explorer leaderboards.

Meta Llama 3 70B by meta-llama — VRAM 141.9GB, 8K context

Name: Meta Llama 3 70B
Author: meta-llama

Meta Llama 3 70B is an open-source language model by meta-llama. Features: 70b LLM, VRAM: 141.9GB, Context: 8K, License: llama3, HF Score: 74, LLM Explorer Score: 0.32, Arc: 68.8, HellaSwag: 88, MMLU: 79.2, TruthfulQA: 45.6, WinoGrande: 85.3, GSM8K: 76.9.

En Endpoints compatible Facebook Llama Llama-3 Meta Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/meta-llama/Meta-Llama-3-70B

Meta Llama 3 70B Benchmarks

IFEval: 16.03 vs 88 (so35)^-81.8%

ARC: 68.77 vs 96.7 (so35)^-28.9%

HellaSwag: 87.98 vs 95.3 (gpt4)^-7.7%

MMLU: 79.23 vs 88.3 (so35)^-10.3%

TruthfulQA: 45.56 vs 59 (gpt4)^-22.8%

WinoGrande: 85.32 vs 87.5 (gpt4)^-2.5%

GSM8K: 76.88 vs 96.4 (so35)^-20.2%

MATH Lvl 5: 18.58

LLME Score: 0.31845

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Meta Llama 3 70B (meta-llama/Meta-Llama-3-70B)

🌟 Advertise your project 🚀

Meta Llama 3 70B Parameters and Internals

Model Type

pre-trained, instruction-tuned, large language model, text generation

Use Cases

Areas:

research, commercial

Applications:

assistant-like chat, natural language generation

Primary Use Cases:

dialogue

Limitations:

English-only currently supported, not tested in all languages

Considerations:

Developers allowed to fine-tune for other languages but must comply with licensing conditions.

Supported Languages

English (high proficiency)

Training Details

Data Sources:

publicly available online data

Data Volume:

15 trillion tokens

Methodology:

supervised fine-tuning, reinforcement learning with human feedback

Context Length:

8000

Hardware Used:

H100-80GB GPUs

Model Architecture:

optimized transformer architecture

Safety Evaluation

Methodologies:

red-teaming, adversarial evaluations

Findings:

reduced false refusals compared to Llama 2

Risk Categories:

disinformation, security, child safety

Ethical Considerations:

Developers advised to perform safety testing and use additional safety tools.

Responsible Ai Considerations

Fairness:

Unspecified

Transparency:

Updates with responsible use guides

Accountability:

Developers responsible for deployment safety

Mitigation Strategies:

Implemented safety mitigation techniques

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text, code

Release Notes

Date:

April 18, 2024

Notes:

Meta Llama 3 final release with benchmarks and community guidelines.

LLM Name	Meta Llama 3 70B
Repository 🤗	https://huggingface.co/meta-llama/Meta-Llama-3-70B
Model Size	70b
Required VRAM	141.9 GB
Updated	2026-04-23
Maintainer	meta-llama
Model Type	llama
Model Files	4.6 GB: 1-of-30 4.7 GB: 2-of-30 5.0 GB: 3-of-30 5.0 GB: 4-of-30 4.7 GB: 5-of-30 4.7 GB: 6-of-30 4.7 GB: 7-of-30 5.0 GB: 8-of-30 5.0 GB: 9-of-30 4.7 GB: 10-of-30 4.7 GB: 11-of-30 4.7 GB: 12-of-30 5.0 GB: 13-of-30 5.0 GB: 14-of-30 4.7 GB: 15-of-30 4.7 GB: 16-of-30 4.7 GB: 17-of-30 5.0 GB: 18-of-30 5.0 GB: 19-of-30 4.7 GB: 20-of-30 4.7 GB: 21-of-30 4.7 GB: 22-of-30 5.0 GB: 23-of-30 5.0 GB: 24-of-30 4.7 GB: 25-of-30 4.7 GB: 26-of-30 4.7 GB: 27-of-30 5.0 GB: 28-of-30 5.0 GB: 29-of-30 2.1 GB: 30-of-30
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	bfloat16

Quantized Models of the Meta Llama 3 70B

Model	Likes	Downloads	VRAM
... 2.9.1 Llama 3 70B 6.0bpw EXL2	3	6	54 GB

Best Alternatives to Meta Llama 3 70B

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	7940	4
... 3 70B Instruct Gradient 1048K	1024K / 141.9 GB	42	122
Llama3 Function Calling 1048K	1024K / 141.9 GB	8	1
...a 3 70B Instruct Gradient 524K	512K / 141.9 GB	293	23
...a 3 70B Instruct Gradient 262K	256K / 141.9 GB	22	56
...ama 3 70B Arimas Story RP V2.0	256K / 141.1 GB	30	3
...ama 3 70B Arimas Story RP V1.6	256K / 141.2 GB	13	0
...ama 3 70B Arimas Story RP V1.5	256K / 141.2 GB	21	3
Yi 70B 200K RPMerge Franken	195K / 142.4 GB	6	1

Rank the Meta Llama 3 70B 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? 53232 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 — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Meta Llama 3 70B by meta-llama