What are the hardware requirements for Llama 2 13B?

Llama 2 13B requires approximately 7.4 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 2 13B and how large is it?

Llama 2 13B is developed by GrazittiInteractive, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama 2 13B perform on standard benchmarks?

Llama 2 13B has the following published scores: MMLU 55.36. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama 2 13B by GrazittiInteractive — VRAM 7.4GB, 4K context

Name: Llama 2 13B
Author: GrazittiInteractive

Llama 2 13B is an open-source language model by GrazittiInteractive. Features: 13b LLM, VRAM: 7.4GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.1, Arc: 59, HellaSwag: 82.3, MMLU: 55.4, GSM8K: 10.

Dataset:meta-llama/llama-2-13b En Facebook Ggml Llama Llama2 Meta Pytorch Q4 Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/GrazittiInteractive/llama-2-13b

Llama 2 13B Parameters and Internals

Model Type

text generation

Use Cases

Areas:

Research, Commercial applications

Primary Use Cases:

Assistant-like chat, Natural language generation tasks

Additional Notes

The provided files are for a quantized version in 4-bit GGML format.

Training Details

Data Sources:

publicly available online data

Data Volume:

2 trillion tokens (pretraining)

Methodology:

Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)

Context Length:

4000

Hardware Used:

Meta's Research Super Cluster, A100-80GB GPUs

Model Architecture:

Auto-regressive transformer architecture

Safety Evaluation

Ethical Considerations:

Requires safety testing and tuning before deployment

Input Output

Input Format:

Text input

Accepted Modalities:

text

Output Format:

Text output

LLM Name	Llama 2 13B
Repository 🤗	https://huggingface.co/GrazittiInteractive/llama-2-13b
Base Model(s)	Ligma L2 13B kubernetes-bad/Ligma-L2-13b
Model Size	13b
Required VRAM	7.4 GB
Updated	2026-08-05
Maintainer	GrazittiInteractive
Model Type	llama
Model Files	7.4 GB
Supported Languages	en
GGML Quantization	Yes
Quantization Type	ggml\|q4
Model Architecture	AutoModelForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0
Vocabulary Size	-1
Torch Data Type	float16

Rank the Llama 2 13B 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 2 13B

Best Alternatives	Context / RAM	Downloads	Likes
...paca 13B Native 4bit 128g Cuda	0K / 7.9 GB	97	9
ALMA 13B R	0K / 26 GB	8766	82
Small Tiny V1	0K / 0.1 GB	10	0
...ama2 13B No Robots Alpaca Lora	0K / 4 GB	58	11
Llava V1.5 13B S2 Lora	0K / 0.1 GB	9	2
Llama 2 13B Chat Hf GPT 4 80K	0K / 26 GB	63	0
Llava Chart 13b Lora	0K / 0.1 GB	4	2
ChartLlama 13B	0K / 0.1 GB	11	20
Orca 2 13B Pygmalion LoRA	0K / 0.5 GB	12	2
Leyley 13B Lora	0K / 4 GB	4	4

Note: green Score (e.g. "73.2") means that the model is better than GrazittiInteractive/llama-2-13b.