What are the hardware requirements for Rhea 125 V0.5?

Rhea 125 V0.5 requires approximately 249 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Rhea 125 V0.5 and how large is it?

Rhea 125 V0.5 is developed by burak, a model with 72b 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 Rhea 125 V0.5?

Rhea 125 V0.5 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Rhea 125 V0.5 by burak — VRAM 249GB, 32K context

Name: Rhea 125 V0.5
Author: burak

Rhea 125 V0.5 is an open-source language model by burak. Features: 72b LLM, VRAM: 249GB, Context: 32K, License: apache-2.0, Merged, LLM Explorer Score: 0.12.

Merged Model Base model:davidkim205/rhea-72... Base model:finetune:davidkim20... Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/burak/Rhea-125-v0.5

Rhea 125 V0.5 Parameters and Internals

Model Type

merge, pre-trained, language models

Additional Notes

This is a merge of pre-trained language models created using mergekit.

LLM Name	Rhea 125 V0.5
Repository 🤗	https://huggingface.co/burak/Rhea-125-v0.5
Base Model(s)	davidkim205/Rhea-72b-v0.5 davidkim205/Rhea-72b-v0.5
Merged Model	Yes
Model Size	72b
Required VRAM	249 GB
Updated	2026-08-04
Maintainer	burak
Model Type	llama
Model Files	9.7 GB: 1-of-26 9.8 GB: 2-of-26 9.9 GB: 3-of-26 9.9 GB: 4-of-26 9.8 GB: 5-of-26 9.9 GB: 6-of-26 9.9 GB: 7-of-26 9.7 GB: 8-of-26 9.9 GB: 9-of-26 9.8 GB: 10-of-26 9.9 GB: 11-of-26 9.9 GB: 12-of-26 9.7 GB: 13-of-26 9.9 GB: 14-of-26 9.8 GB: 15-of-26 9.9 GB: 16-of-26 9.9 GB: 17-of-26 9.7 GB: 18-of-26 9.9 GB: 19-of-26 9.8 GB: 20-of-26 9.9 GB: 21-of-26 9.9 GB: 22-of-26 9.7 GB: 23-of-26 9.7 GB: 24-of-26 9.9 GB: 25-of-26 3.2 GB: 26-of-26
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.3
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	152064
Torch Data Type	bfloat16

Rank the Rhea 125 V0.5 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 Rhea 125 V0.5

Best Alternatives	Context / RAM	Downloads	Likes
2 Pro Math	128K / 141.9 GB	10	0
TW3 JRGL V2	32K / 79.7 GB	16209	0
Le Triomphant ECE TW3	32K / 79.7 GB	16266	5
Smaug 72B V0.1	32K / 144.5 GB	8736	468
ECE TW3 JRGL V5	32K / 159.6 GB	8245	1
MoMo 72B Lora 1.8.7 DPO	32K / 208.5 GB	314	68
Rhea 72B V0.5	32K / 144.5 GB	8194	134
JuliusCesar 72B BeyonderV.0	32K / 74.2 GB	77	0
Caigun Model 72B KGI	32K / 144.6 GB	31	0
Exodius 70B	32K / 144.6 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than burak/Rhea-125-v0.5.