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

Llama 3.2 3B Instruct requires approximately 6.5 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 3B Instruct and how large is it?

Llama 3.2 3B Instruct is developed by unsloth, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 3.2 3B Instruct perform on standard benchmarks?

Llama 3.2 3B Instruct has the following published scores: LMSYS ELO 1167. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 3.2 3B Instruct by unsloth — VRAM 6.5GB, 128K context

Name: Llama 3.2 3B Instruct
Author: unsloth

Llama 3.2 3B Instruct is an open-source language model by unsloth. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, License: llama3.2, Instruction-Based, LLM Explorer Score: 0.34, ELO: 1167.

Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Conversational Deploy:azure En Endpoints compatible Facebook Instruct Llama Llama-3 Meta Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/unsloth/Llama-3.2-3B-Instruct

Llama 3.2 3B Instruct Benchmarks

LMSys ELO 1167 vs 1272 (so35) -8.3%

^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 3B Instruct Parameters and Internals

Model Type

auto-regressive, transformer, text generation

Use Cases

Areas:

multilingual dialogue use cases

Primary Use Cases:

agentic retrieval, summarization tasks

Additional Notes

Future versions may be released that improve model capabilities and safety.

Supported Languages

English (official), German (official), French (official), Italian (official), Portuguese (official), Hindi (official), Spanish (official), Thai (official)

Training Details

Methodology:

supervised fine-tuning, reinforcement learning with human feedback (RLHF)

Model Architecture:

optimized transformer architecture

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text

Release Notes

Date:

Sept 25, 2024

Notes:

This is a static model trained on an offline dataset.

LLM Name	Llama 3.2 3B Instruct
Repository 🤗	https://huggingface.co/unsloth/Llama-3.2-3B-Instruct
Base Model(s)	meta-llama/Llama-3.2-3B-Instruct meta-llama/Llama-3.2-3B-Instruct
Model Size	3b
Required VRAM	6.5 GB
Updated	2026-08-08
Maintainer	unsloth
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 1.5 GB: 2-of-2
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	llama3.2
Context Length	131072
Model Max Length	131072
Transformers Version	4.52.4
Tokenizer Class	PreTrainedTokenizer
Padding Token	<\|finetune_right_pad_id\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3.2 3B Instruct 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 Llama 3.2 3B Instruct

Model	Likes	Downloads	VRAM
Llama 3.2 3B Reflect	1	546	6 GB
ReWiz Llama 3.2 3B	3	341	6 GB

Best Alternatives to Llama 3.2 3B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368
Llama 3.2 3B ClauseLM	128K / 6.4 GB	335	2
...ld Llama32 3B Instruct Qa 1p25	128K / 6.5 GB	340	1
...old Llama32 3B Instruct Qa 2p5	128K / 6.5 GB	334	1
...lama 3.2 3B ORPO Advertisement	128K / 6.5 GB	189	2
...3B TechWriter Instruct Unsloth	128K / 6.5 GB	627	1
...ini Math345 GroupB Llama32 End	128K / 6.5 GB	755	0
...ama 3.2 3B TechWriter Instruct	128K / 6.4 GB	226	0
Llama 3.2 3B Instruct	128K / 6.5 GB	991	9
Alloma 3B Instruct	128K / 6.5 GB	55456	6

Note: green Score (e.g. "73.2") means that the model is better than unsloth/Llama-3.2-3B-Instruct.