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

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit requires approximately 9.5 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 2bit and how large is it?

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

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit 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 2bit by Yhyu13 — VRAM 9.5GB, 2K context

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

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit is an open-source language model by Yhyu13. Features: 30b LLM, VRAM: 9.5GB, Context: 2K, Quantized, LLM Explorer Score: 0.11, Arc: 61.4, HellaSwag: 83.8, MMLU: 57.9, GSM8K: 31.5.

2bit Endpoints compatible Gptq Llama Pytorch Quantized Region:us

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

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit Benchmarks

ARC: 61.35 vs 96.7 (so35)^-36.6%

HellaSwag: 83.8 vs 95.3 (gpt4)^-12.1%

MMLU: 57.89 vs 88.3 (so35)^-34.4%

GSM8K: 31.46 vs 96.4 (so35)^-67.4%

LLME Score: 0.10523

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit (Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-2bit)

🌟 Advertise your project 🚀

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

Model Type

text generation

Additional Notes

This model version is generated for compatibility with textgen-webui using 2-bit GPTQ quantization, created using scripts from Yhyu13's Gitee repository.

LLM Name	Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit
Repository 🤗	https://huggingface.co/Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-2bit
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	9.5 GB
Updated	2026-05-17
Maintainer	Yhyu13
Model Type	llama
Model Files	9.5 GB
GPTQ Quantization	Yes
Quantization Type	gptq\|2bit
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32006
Torch Data Type	float16

Best Alternatives to Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit

Best Alternatives	Context / RAM	Downloads	Likes
GPlatty 30B SuperHOT 8K GPTQ	8K / 16.9 GB	76	7
Tulu 30B SuperHOT 8K GPTQ	8K / 16.9 GB	68	5
... 30B Supercot SuperHOT 8K GPTQ	8K / 16.9 GB	9	5
Platypus 30B SuperHOT 8K GPTQ	8K / 16.9 GB	10	4
Yayi2 30B Llama GPTQ	4K / 17 GB	11	2
WizardLM 30B GPTQ	2K / 16.9 GB	229	18
Llama 30B FINAL MODEL MINI	2K / 19.4 GB	7	1
WizardLM 30B V1.0 GPTQ	2K / 16.9 GB	2	1
...Assistant SFT 7 Llama 30B GPTQ	2K / 16.9 GB	218	35
...2 Llama 30B 7K Steps Gptq 4bit	2K / 17.5 GB	7	3

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

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

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit by Yhyu13

» All LLMs » Yhyu13 » Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit URL Share it on

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit Benchmarks

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

Best Alternatives to Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit

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

What open-source LLMs or SLMs are you in search of? 53999 in total.