What are the hardware requirements for Rhea 72B V0.5 4bit 128g?

Rhea 72B V0.5 4bit 128g requires approximately 41.3 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 72B V0.5 4bit 128g and how large is it?

Rhea 72B V0.5 4bit 128g is developed by titan087, 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 72B V0.5 4bit 128g?

Rhea 72B V0.5 4bit 128g is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Rhea 72B V0.5 4bit 128g by titan087 — VRAM 41.3GB, 32K context

Name: Rhea 72B V0.5 4bit 128g
Author: titan087

Rhea 72B V0.5 4bit 128g is an open-source language model by titan087. Features: 72b LLM, VRAM: 41.3GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.11.

4-bit 4bit En Endpoints compatible Gptq Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/titan087/Rhea-72b-v0.5-4bit-128g

Rhea 72B V0.5 4bit 128g Parameters and Internals

Model Type

fine-tuned, self-supervised learning

Additional Notes

Rhea project conducts research on various learning methods to improve LLM model performance, including creating datasets using SGD.

Supported Languages

en (proficient)

Training Details

Methodology:

fine-tuning using the nox framework, Self-Generated Dataset Creation Method for DPO Learning (SGD)

LLM Name	Rhea 72B V0.5 4bit 128g
Repository 🤗	https://huggingface.co/titan087/Rhea-72b-v0.5-4bit-128g
Model Size	72b
Required VRAM	41.3 GB
Updated	2026-07-25
Maintainer	titan087
Model Type	llama
Model Files	41.3 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq\|4bit
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.0.dev0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	152064
Torch Data Type	float16

Rank the Rhea 72B V0.5 4bit 128g 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 72B V0.5 4bit 128g

Best Alternatives	Context / RAM	Downloads	Likes
Smaug 72B V0.1 GPTQ	32K / 41.3 GB	5	2
Smaug 72B V0.1 GPTQ	32K / 41.3 GB	4	8
MoMo 72B Lora 1.8.7 DPO GPTQ	32K / 41.3 GB	2	7
Smaug 72B V0.1 2.4bpw H6 EXL2	32K / 24.5 GB	4	1
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

Note: green Score (e.g. "73.2") means that the model is better than titan087/Rhea-72b-v0.5-4bit-128g.