What are the hardware requirements for Nous Hermes Llama2 13B?

Nous Hermes Llama2 13B requires approximately 26 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 Nous Hermes Llama2 13B and how large is it?

Nous Hermes Llama2 13B is developed by NousResearch, 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 Nous Hermes Llama2 13B perform on standard benchmarks?

Nous Hermes Llama2 13B has the following published scores: MMLU 55.04. Compare against reference models on this page or on the LLM Explorer leaderboards.

Nous Hermes Llama2 13B by NousResearch — VRAM 26GB, 4K context

Name: Nous Hermes Llama2 13B
Author: NousResearch

Nous Hermes Llama2 13B is an open-source language model by NousResearch. Features: 13b LLM, VRAM: 26GB, Context: 4K, License: mit, LLM Explorer Score: 0.12, Arc: 61.3, HellaSwag: 83.3, MMLU: 55, GSM8K: 9.2.

Deploy:azure Distillation En Endpoints compatible Llama Llama2 Pytorch Region:us Safetensors Self-instruct Sharded Synthetic instruction Tensorflow

Model Card on HF 🤗: https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b

Nous Hermes Llama2 13B Parameters and Internals

Model Type

language model

Use Cases

Areas:

commercial applications, research

Applications:

language tasks, generating creative text, following complex instructions

Training Details

Data Sources:

GPTeacher, general, roleplay v1&2, code instruct datasets, Nous Instruct & PDACTL, Wizard LM, GPT4-LLM, Unnatural Instructions, Airoboros, Camel-AI, CodeAlpaca

Methodology:

Fine-tuned on over 300,000 instructions

Context Length:

4096

Hardware Used:

8x a100 80GB DGX machine

Input Output

Input Format:

Alpaca prompt format

Accepted Modalities:

text

LLM Name	Nous Hermes Llama2 13B
Repository 🤗	https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b
Model Size	13b
Required VRAM	26 GB
Updated	2026-08-05
Maintainer	NousResearch
Model Type	llama
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3 9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.32.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32032
Torch Data Type	bfloat16

Rank the Nous Hermes Llama2 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

Quantized Models of the Nous Hermes Llama2 13B

Model	Likes	Downloads	VRAM
Nous Hermes Llama2 GGUF	18	1620	5 GB
Nous Hermes Llama2 AWQ	1	8	7 GB
Nous Hermes Llama2 GGML	101	7	5 GB
Nous Hermes Llama2 GPTQ	60	76	7 GB

Best Alternatives to Nous Hermes Llama2 13B

Best Alternatives	Context / RAM	Downloads	Likes
Luminaura RP 13B	128K / 26 GB	9	1
Yarn Llama 2 13B 128K	128K / 26 GB	184	113
Agent Llama2 13B 80K	80K / 26.4 GB	5	0
Chat Llama2 13B 80K	80K / 52.8 GB	5	0
LongAlign 13B 64K	64K / 26 GB	96	13
LongAlign 13B 64K Base	64K / 26 GB	89	3
LongAlign 13B 64K	64K / 26 GB	11	13
LongAlign 13B 64K Base	64K / 26 GB	6	3
Openbuddy Llama2 13B V15p1 64K	64K / 26.1 GB	4	4
Openbuddy Llama2 13b64k V15	64K / 26.1 GB	12	2

Note: green Score (e.g. "73.2") means that the model is better than NousResearch/Nous-Hermes-Llama2-13b.