What are the hardware requirements for Llama 3.2 SARA 3B?

Llama 3.2 SARA 3B requires approximately 7.2 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3.2 SARA 3B and how large is it?

Llama 3.2 SARA 3B is developed by EryriLabs, a model with 3b 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 3.2 SARA 3B?

Llama 3.2 SARA 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 3.2 SARA 3B by EryriLabs — VRAM 7.2GB, 128K context

Name: Llama 3.2 SARA 3B
Author: EryriLabs

Llama 3.2 SARA 3B is an open-source language model by EryriLabs. Features: 3b LLM, VRAM: 7.2GB, Context: 128K, License: llama3.2, Quantized, LLM Explorer Score: 0.16.

4bit Base model:finetune:unsloth/ll... Base model:unsloth/llama-3.2-3... En Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/EryriLabs/Llama-3.2-SARA-3b

Llama 3.2 SARA 3B Benchmarks

LLME Score: 0.16237

^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)

Llama 3.2 SARA 3B (EryriLabs/Llama-3.2-SARA-3b)

🌟 Advertise your project 🚀

Llama 3.2 SARA 3B Parameters and Internals

LLM Name	Llama 3.2 SARA 3B
Repository 🤗	https://huggingface.co/EryriLabs/Llama-3.2-SARA-3b
Base Model(s)	unsloth/Llama-3.2-3B-bnb-4bit unsloth/Llama-3.2-3B-bnb-4bit
Model Size	3b
Required VRAM	7.2 GB
Updated	2026-04-27
Maintainer	EryriLabs
Model Type	llama
Model Files	5.0 GB: 1-of-2 2.2 GB: 2-of-2
Supported Languages	en
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
License	llama3.2
Context Length	131072
Model Max Length	131072
Transformers Version	4.46.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|finetune_right_pad_id\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Best Alternatives to Llama 3.2 SARA 3B

Best Alternatives	Context / RAM	Downloads	Likes
Nanbeige4.1 3B 8bit	256K / 4.2 GB	332	14
Nanbeige4.1 3B Heretic 8bit	256K / 4.2 GB	74	2
Llama3.2 3B Base Math	128K / 6.5 GB	540	0
Llama3.2 3B Base Code	128K / 6.5 GB	453	0
...2 3B Instruct Unsloth Bnb 4bit	128K / 2.4 GB	106422	10
Llama32 3B En Emo 2000 Stp	128K / 2.2 GB	95	0
Llama32 3B En Emo 300 Stp	128K / 2.2 GB	9	0
Llama32 3B En Emo 1000 Stp	128K / 2.2 GB	6	0
Llama32 3B En Emo 5000 Stp	128K / 2.2 GB	5	0
...ngCore 3B Instruct R01 Reflect	128K / 6.5 GB	0	1

Note: green Score (e.g. "73.2") means that the model is better than EryriLabs/Llama-3.2-SARA-3b.

Rank the Llama 3.2 SARA 3B 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? 53444 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

Llama 3.2 SARA 3B by EryriLabs

» All LLMs » EryriLabs » Llama 3.2 SARA 3B URL Share it on

Llama 3.2 SARA 3B Benchmarks

Llama 3.2 SARA 3B Parameters and Internals

Best Alternatives to Llama 3.2 SARA 3B

Rank the Llama 3.2 SARA 3B Capabilities

What open-source LLMs or SLMs are you in search of? 53444 in total.