What are the hardware requirements for Llama 3.2 3B Instruct Bnb 4bit?

Llama 3.2 3B Instruct Bnb 4bit requires approximately 2.2 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 3B Instruct Bnb 4bit and how large is it?

Llama 3.2 3B Instruct Bnb 4bit 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.

Where can I download or evaluate Llama 3.2 3B Instruct Bnb 4bit?

Llama 3.2 3B Instruct Bnb 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 3.2 3B Instruct Bnb 4bit by unsloth — VRAM 2.2GB, 128K context

Name: Llama 3.2 3B Instruct Bnb 4bit
Author: unsloth

Llama 3.2 3B Instruct Bnb 4bit is an open-source language model by unsloth. Features: 3b LLM, VRAM: 2.2GB, Context: 128K, License: llama3.2, Quantized, Instruction-Based, LLM Explorer Score: 0.21.

4-bit 4bit Base model:meta-llama/llama-3.... Base model:quantized:meta-llam... Bitsandbytes Conversational Deploy:azure En Endpoints compatible Facebook Instruct Llama Llama-3 Meta Quantized Region:us Safetensors Unsloth

Model Card on HF 🤗: https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit

Llama 3.2 3B Instruct Bnb 4bit Benchmarks

LLME Score: 0.21402

^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 Bnb 4bit (unsloth/Llama-3.2-3B-Instruct-bnb-4bit)

🌟 Advertise your project 🚀

Llama 3.2 3B Instruct Bnb 4bit Parameters and Internals

Model Type

text generation

Additional Notes

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

Supported Languages

en (high), de (high), fr (high), it (high), pt (high), hi (high), es (high), th (high)

Training Details

Methodology:

The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.

Model Architecture:

Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture.

Input Output

Input Format:

text in

Output Format:

text out

LLM Name	Llama 3.2 3B Instruct Bnb 4bit
Repository 🤗	https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit
Base Model(s)	meta-llama/Llama-3.2-3B-Instruct meta-llama/Llama-3.2-3B-Instruct
Model Size	3b
Required VRAM	2.2 GB
Updated	2026-05-19
Maintainer	unsloth
Model Type	llama
Instruction-Based	Yes
Model Files	2.2 GB
Supported Languages	en
Quantization Type	4bit
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

Quantized Models of the Llama 3.2 3B Instruct Bnb 4bit

Model	Likes	Downloads	VRAM
Llama32 Legal Id Sft	0	110	6 GB
Llama3 2 3B Indonesian Sft	0	19	2 GB
PSC	0	16	0 GB
Llama32 3B En Emo V3	0	12	2 GB
Llama32 3B En Emo V2	1	5	2 GB
FineTome Llama3.2 3B 1002	1	5	6 GB
Llama32 1B En Emo V1	0	5	1 GB
...2 3B Instruct En Hi Merge 200K	0	5	6 GB
Llama3.2	0	5	7 GB
...Llama 3.2 3B Instruct Bnb 4bit	2	5	6 GB

Best Alternatives to Llama 3.2 3B Instruct Bnb 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Llama32 Legal Id Sft	128K / 6.5 GB	110	0
Llama 3.2 3B Legal SFT	128K / 6.5 GB	41	0
Llama3.2 3B INST Math1	128K / 6.5 GB	97	0
Llama3 2 3B Indonesian Sft	128K / 2.2 GB	19	0
Llama32 3B En Emo 2000 Stp	128K / 2.2 GB	17	1
Llama32 3B En Emo 300 Stp	128K / 2.2 GB	9	0
Llama32 3B En Emo 1000 Stp	128K / 2.2 GB	5	0
Llama32 3B En Emo 5000 Stp	128K / 2.2 GB	6	0
...ngCore 3B Instruct R01 Reflect	128K / 6.5 GB	0	1
ReasoningCore 3B 0	128K / 6.5 GB	35	2

Note: green Score (e.g. "73.2") means that the model is better than unsloth/Llama-3.2-3B-Instruct-bnb-4bit.

Rank the Llama 3.2 3B Instruct Bnb 4bit 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? 54780 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 3B Instruct Bnb 4bit by unsloth