What are the hardware requirements for Nous Hermes Llama2 70B GGML?

Nous Hermes Llama2 70B GGML requires approximately 29 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nous Hermes Llama2 70B GGML and how large is it?

Nous Hermes Llama2 70B GGML is developed by TheBloke, a model with 70b 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 70B GGML?

Nous Hermes Llama2 70B 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 70B GGML by TheBloke — VRAM 29GB

Name: Nous Hermes Llama2 70B GGML
Author: TheBloke

Nous Hermes Llama2 70B GGML is an open-source language model by TheBloke. Features: 70b LLM, VRAM: 29GB, 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-Llama2-70B-GGML

Nous Hermes Llama2 70B GGML Parameters and Internals

Model Type

llama

Additional Notes

This model offers long responses, lower hallucination rate, and is not subject to OpenAI censorship of training data. Uses GGML and GGUF formats, with Llama 70B GPU acceleration options.

Training Details

Data Sources:

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

Methodology:

Fine-tuning with synthetic GPT-4 outputs and Alpaca prompt format.

Context Length:

4096

Hardware Used:

8x H100 80GB machine

LLM Name	Nous Hermes Llama2 70B GGML
Repository 🤗	https://huggingface.co/TheBloke/Nous-Hermes-Llama2-70B-GGML
Model Name	Nous Hermes Llama2 70B
Model Creator	NousResearch
Base Model(s)	Nous Hermes Llama2 70B NousResearch/Nous-Hermes-Llama2-70b
Model Size	70b
Required VRAM	29 GB
Updated	2026-07-29
Maintainer	TheBloke
Model Type	llama
Model Files	29.0 GB 36.5 GB 33.4 GB 30.1 GB 38.8 GB 43.1 GB 41.7 GB 39.2 GB 47.4 GB 49.0 GB 47.7 GB
Supported Languages	en
GGML Quantization	Yes
Quantization Type	ggml
Model Architecture	AutoModel
License	llama2

Rank the Nous Hermes Llama2 70B 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 70B GGML

Best Alternatives	Context / RAM	Downloads	Likes
Synthia 70B V1.1 GGML	0K / 28.6 GB	3	4
...boros L2 70B 2.1 Creative GGML	0K / 28.6 GB	4	3
...iction.live Kimiko V2 70B GGML	0K / 28.6 GB	8	2
Llama 2 70B Chat GGML	0K / 28.6 GB	10	161
Lemur 70B Chat V1 GGML	0K / 29 GB	4	3
Model 007 70B GGML	0K / 28.6 GB	6	1
Airoboros L2 70B 2.1 GGML	0K / 28.6 GB	6	2
Llama 2 70B Orca 200K GGML	0K / 28.6 GB	7	3
Genz 70B GGML	0K / 28.6 GB	6	3
Synthia 70B GGML	0K / 28.6 GB	3	2

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Nous-Hermes-Llama2-70B-GGML.