What are the hardware requirements for Prometheus 2 Llama 3 8B?

Prometheus 2 Llama 3 8B requires approximately 16.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Prometheus 2 Llama 3 8B and how large is it?

Prometheus 2 Llama 3 8B is developed by chargoddard, a model with 8b 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 Prometheus 2 Llama 3 8B?

Prometheus 2 Llama 3 8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Prometheus 2 Llama 3 8B by chargoddard — VRAM 16.1GB, 8K context

Name: Prometheus 2 Llama 3 8B
Author: chargoddard

Prometheus 2 Llama 3 8B is an open-source language model by chargoddard. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: apache-2.0, Merged, LLM Explorer Score: 0.18.

Merged Model Arxiv:2310.08491 Arxiv:2405.01535 Base model:chargoddard/prometh... Base model:chargoddard/prometh... Conversational Dataset:prometheus-eval/feedba... Dataset:prometheus-eval/prefer... En Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/chargoddard/prometheus-2-llama-3-8b

Prometheus 2 Llama 3 8B Parameters and Internals

Model Type

text generation, evaluation

Use Cases

Areas:

Research, Language Evaluation

Additional Notes

Replication of prometheus-7b-v2.0 using Llama 3 8B Instruct as a base model.

Supported Languages

en (Full proficiency)

Training Details

Data Sources:

prometheus-eval/Preference-Collection, prometheus-eval/Feedback-Collection

Methodology:

Two different models were trained on preference and feedback datasets then linearly merged at equal weight using training hyperparameters: 1 epoch, learning rate 1e-5, effective batch size 128, cosine annealing, ~5% warmup.

Model Architecture:

Using Llama 3 8B Instruct as a base model

LLM Name	Prometheus 2 Llama 3 8B
Repository 🤗	https://huggingface.co/chargoddard/prometheus-2-llama-3-8b
Base Model(s)	chargoddard/prometheus-llama-3-8b-preference chargoddard/prometheus-llama-3-8b-absolute chargoddard/prometheus-llama-3-8b-preference chargoddard/prometheus-llama-3-8b-absolute
Merged Model	Yes
Model Size	8b
Required VRAM	16.1 GB
Updated	2026-08-05
Maintainer	chargoddard
Model Type	llama
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Prometheus 2 Llama 3 8B 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 Prometheus 2 Llama 3 8B

Best Alternatives	Context / RAM	Downloads	Likes
...otron 8B UltraLong 4M Instruct	4192K / 32.1 GB	1135	125
UltraLong Thinking	4192K / 16.1 GB	2	3
...a 3.1 8B UltraLong 4M Instruct	4192K / 32.1 GB	176	24
...a 3.1 8B UltraLong 2M Instruct	2096K / 32.1 GB	875	9
...otron 8B UltraLong 2M Instruct	2096K / 32.1 GB	124	18
Cthulhu 8B V1.4	1048K / 16.1 GB	10	10
...raLong 1M Instruct Abliterated	1048K / 32.1 GB	4	9
...a 3.1 8B UltraLong 1M Instruct	1048K / 32.1 GB	1387	29
...otron 8B UltraLong 1M Instruct	1048K / 32.1 GB	702	59
...xis Bookwriter Llama3.1 8B Sft	1048K / 16.1 GB	25	4

Note: green Score (e.g. "73.2") means that the model is better than chargoddard/prometheus-2-llama-3-8b.