What are the hardware requirements for Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit?

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit requires approximately 17.5 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit and how large is it?

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit is developed by Yhyu13, a model with 30b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit perform on standard benchmarks?

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit has the following published scores: MMLU 57.89. Compare against reference models on this page or on the LLM Explorer leaderboards.

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit by Yhyu13 — VRAM 17.5GB, 2K context

Name: Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit
Author: Yhyu13

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit is an open-source language model by Yhyu13. Features: 30b LLM, VRAM: 17.5GB, Context: 2K, License: apache-2.0, Quantized, LLM Explorer Score: 0.09, Arc: 61.4, HellaSwag: 83.8, MMLU: 57.9, GSM8K: 31.5.

4bit Endpoints compatible Gptq Llama Pytorch Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-4bit

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit Parameters and Internals

Model Type

Text Generation

Additional Notes

OA has implemented Reinforcement Learning from Human Feedback (RLHF) and observed a notable improvement in step-by-step thinking (similar to GPT-4 and ChatGPT) but it struggles with logical paradox tasks. It provides a professional tone in responses.

LLM Name	Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit
Repository 🤗	https://huggingface.co/Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-4bit
Base Model(s)	...t Rlhf 2 Llama 30B 7K Steps Hf Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-hf
Model Size	30b
Required VRAM	17.5 GB
Updated	2026-08-01
Maintainer	Yhyu13
Model Type	llama
Model Files	17.5 GB
GPTQ Quantization	Yes
Quantization Type	gptq\|4bit
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32006
Torch Data Type	float16

Rank the Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit 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 Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit

Best Alternatives	Context / RAM	Downloads	Likes
... 30B Supercot SuperHOT 8K GPTQ	8K / 16.9 GB	69	5
GPlatty 30B SuperHOT 8K GPTQ	8K / 16.9 GB	10	7
Platypus 30B SuperHOT 8K GPTQ	8K / 16.9 GB	5	4
Tulu 30B SuperHOT 8K GPTQ	8K / 16.9 GB	8	5
Yayi2 30B Llama GPTQ	4K / 17 GB	12	2
WizardLM 30B GPTQ	2K / 16.9 GB	645	18
...2 Llama 30B 7K Steps Gptq 2bit	2K / 9.5 GB	9	2
Llama 30B FINAL MODEL MINI	2K / 19.4 GB	5	1
WizardLM 30B V1.0 GPTQ	2K / 16.9 GB	4	1
...Assistant SFT 7 Llama 30B GPTQ	2K / 16.9 GB	124	35

Note: green Score (e.g. "73.2") means that the model is better than Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-4bit.