What are the hardware requirements for Nous Hermes Llama2 GGML?

Nous Hermes Llama2 GGML requires approximately 5.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nous Hermes Llama2 GGML and how large is it?

Nous Hermes Llama2 GGML is developed by TheBloke, a model with 13b 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 Nous Hermes Llama2 GGML?

Nous Hermes Llama2 GGML is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nous Hermes Llama2 GGML by TheBloke — VRAM 5.7GB

Name: Nous Hermes Llama2 GGML
Author: TheBloke

Nous Hermes Llama2 GGML is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 5.7GB, License: llama2, Quantized, LLM Explorer Score: 0.08.

Base model:finetune:nousresear... Base model:nousresearch/nous-h... Distillation En Ggml Llama Llama2 Quantized Region:us Self-instruct Synthetic instruction

Model Card on HF 🤗: https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GGML

Nous Hermes Llama2 GGML Parameters and Internals

Model Type

llama

Additional Notes

The model is fine-tuned on over 300,000 instructions with a focus on long responses, and a lower hallucination rate. Original model data from synthetic GPT-4 outputs allow it to perform well in knowledge, task completion, and style. The model follows the Alpaca prompt format.

Training Details

Data Sources:

GPT-4 outputs, GPTeacher, Wizard LM, Nous Research Instruct Dataset, GPT4-LLM, Unnatural Instructions, Airoboros dataset, Camel-AI's domain expert datasets, CodeAlpaca dataset

Methodology:

Fine-tuning on over 300,000 instructions using Alpaca format

Context Length:

4096

Hardware Used:

8x A100 80GB DGX machine

LLM Name	Nous Hermes Llama2 GGML
Repository 🤗	https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GGML
Model Name	Nous Hermes Llama 2 13B
Model Creator	NousResearch
Base Model(s)	Nous Hermes Llama2 13B NousResearch/Nous-Hermes-Llama2-13b
Model Size	13b
Required VRAM	5.7 GB
Updated	2026-07-31
Maintainer	TheBloke
Model Type	llama
Model Files	5.7 GB 7.1 GB 6.5 GB 5.9 GB 7.3 GB 8.1 GB 8.1 GB 7.6 GB 8.9 GB 9.8 GB 9.4 GB 9.2 GB 10.8 GB 13.8 GB
Supported Languages	en
GGML Quantization	Yes
Quantization Type	ggml
Model Architecture	AutoModel
License	llama2

Rank the Nous Hermes Llama2 GGML 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 Nous Hermes Llama2 GGML

Best Alternatives	Context / RAM	Downloads	Likes
Llama 2 13B Chat GGML	0K / 5.5 GB	158	693
RuGPT 3.5 13B GGML	0K / 7.4 GB	10	8
RuGPT 3.5 13B GGML	0K / 7.4 GB	10	15
...penBuddy Llama2 13B V11.1 GGML	0K / 5.5 GB	11	5
...rca Platypus WizardLM 13B GGML	0K / 5.5 GB	6	6
Speechless Llama2 13B GGML	0K / 5.5 GB	4	2
Yarn Llama 2 13B 128K GGML	0K / 5.5 GB	5	6
Yarn Llama 2 13B 64K GGML	0K / 5.5 GB	7	5
Stheno L2 13B GGML	0K / 5.5 GB	7	5
Asclepius 13B GGML	0K / 5.5 GB	6	1

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