What are the hardware requirements for Llama 3.1 Tango 70B?

Llama 3.1 Tango 70B requires approximately 3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3.1 Tango 70B and how large is it?

Llama 3.1 Tango 70B is developed by sandbox-ai, 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 Llama 3.1 Tango 70B?

Llama 3.1 Tango 70B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 3.1 Tango 70B by sandbox-ai — VRAM 3GB

Name: Llama 3.1 Tango 70B
Author: sandbox-ai

Llama 3.1 Tango 70B is an open-source language model by sandbox-ai. Features: 70b LLM, VRAM: 3GB, License: llama3.1, Instruction-Based, LLM Explorer Score: 0.15.

Arxiv:2409.05994 Arxiv:2410.01257 Base model:finetune:nvidia/lla... Base model:nvidia/llama-3.1-ne... Dataset:spanish-ir/messirve En Es Instruct Llama Llama3.1 Lora Nvidia Region:us Safetensors Spanish Tango

Model Card on HF 🤗: https://huggingface.co/sandbox-ai/Llama-3.1-Tango-70b

Llama 3.1 Tango 70B Parameters and Internals

LLM Name	Llama 3.1 Tango 70B
Repository 🤗	https://huggingface.co/sandbox-ai/Llama-3.1-Tango-70b
Base Model(s)	nvidia/Llama-3.1-Nemotron-70B-Instruct-HF nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Model Size	70b
Required VRAM	3 GB
Updated	2026-05-23
Maintainer	sandbox-ai
Instruction-Based	Yes
Model Files	3.0 GB
Supported Languages	en es
Model Architecture	AutoModelForCausalLM
License	llama3.1
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	gate_proj\|down_proj\|k_proj\|v_proj\|up_proj\|q_proj
LoRA Alpha	16
LoRA Dropout	0.1
R Param	64

Rank the Llama 3.1 Tango 70B 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 Llama 3.1 Tango 70B

Best Alternatives	Context / RAM	Downloads	Likes
... 70M Instruct Orca Chkpt 64000	0K / 0.2 GB	8	1
...3 70B Instruct Uncensored Lora	0K / 0.8 GB	8	3