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

Llama 3.2 3B NuminaQA requires approximately 12.8 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Llama 3.2 3B NuminaQA is developed by lkevinzc, 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 NuminaQA?

Llama 3.2 3B NuminaQA 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 NuminaQA by lkevinzc — VRAM 12.8GB, 4K context

Name: Llama 3.2 3B NuminaQA
Author: lkevinzc

Llama 3.2 3B NuminaQA is an open-source language model by lkevinzc. Features: 3b LLM, VRAM: 12.8GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.17.

Arxiv:2503.20783 Base model:finetune:huggingfac... Base model:huggingfacetb/finem... Dataset:lkevinzc/numia-1.5-qa-... Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

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

Llama 3.2 3B NuminaQA Parameters and Internals

LLM Name	Llama 3.2 3B NuminaQA
Repository 🤗	https://huggingface.co/lkevinzc/Llama-3.2-3B-NuminaQA
Base Model(s)	FineMath Llama 3B HuggingFaceTB/FineMath-Llama-3B
Model Size	3b
Required VRAM	12.8 GB
Updated	2026-07-25
Maintainer	lkevinzc
Model Type	llama
Model Files	5.0 GB: 1-of-3 4.9 GB: 2-of-3 2.9 GB: 3-of-3
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.48.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	float32

Rank the Llama 3.2 3B NuminaQA 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 3.2 3B NuminaQA

Best Alternatives	Context / RAM	Downloads	Likes
Nanbeige4.1 3B	256K / 7.9 GB	20875	1161
Nanbeige4.1 3B Heretic	256K / 7.9 GB	149	50
Nanbeige4.1 3B Heretic Mxfp4	256K / 7.9 GB	34	2
Nanbeige4.1 3B Bf16	256K / 7.9 GB	47	3
Nanbeige4.1 3B Heretic	256K / 7.9 GB	14	1
Nanbeige4.1 3B Heretic	256K / 7.9 GB	7	0
ISA 03 Mini 3B Hybrid Preview	256K / 6.5 GB	4	4
ToolMind Web 3B	192K / 7.9 GB	156	28
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368
G9v3 3B	128K / 6 GB	2670	31

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