What are the hardware requirements for Upstage Llama 30B Instruct 2048 GPTQ?

Upstage Llama 30B Instruct 2048 GPTQ requires approximately 16.9 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 Upstage Llama 30B Instruct 2048 GPTQ and how large is it?

Upstage Llama 30B Instruct 2048 GPTQ is developed by TheBloke, a model with 30b 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 Upstage Llama 30B Instruct 2048 GPTQ?

Upstage Llama 30B Instruct 2048 GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Upstage Llama 30B Instruct 2048 GPTQ by TheBloke — VRAM 16.9GB, 2K context

Name: Upstage Llama 30B Instruct 2048 GPTQ
Author: TheBloke

Upstage Llama 30B Instruct 2048 GPTQ is an open-source language model by TheBloke. Features: 30b LLM, VRAM: 16.9GB, Context: 2K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.08.

4-bit Base model:quantized:upstage/l... Base model:upstage/llama-30b-i... Dataset:gair/lima Dataset:metaeval/scienceqa tex... Dataset:open-orca/openorca Dataset:openbookqa Dataset:sciq En Gptq Instruct Instruction Llama Quantized Region:us Safetensors Upstage

Model Card on HF 🤗: https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ

Upstage Llama 30B Instruct 2048 GPTQ Parameters and Internals

Model Type

llama

Supported Languages

English (Fluent)

Training Details

Data Sources:

openbookqa, sciq, Open-Orca/OpenOrca, metaeval/ScienceQA_text_only, GAIR/lima

Context Length:

2048

Hardware Used:

A100x8

Model Architecture:

LLaMA

Input Output

Input Format:

Prompt template: ### System: {system_message} ### User: {prompt} ### Assistant:

Accepted Modalities:

text

Output Format:

text

LLM Name	Upstage Llama 30B Instruct 2048 GPTQ
Repository 🤗	https://huggingface.co/TheBloke/upstage-llama-30b-instruct-2048-GPTQ
Model Name	Llama 30B Instruct 2048
Model Creator	upstage
Base Model(s)	Llama 30B Instruct 2048 upstage/llama-30b-instruct-2048
Model Size	30b
Required VRAM	16.9 GB
Updated	2026-06-06
Maintainer	TheBloke
Model Type	llama
Instruction-Based	Yes
Model Files	16.9 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.30.2
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Upstage Llama 30B Instruct 2048 GPTQ 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 Upstage Llama 30B Instruct 2048 GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
H2ogpt Oasst1 512 30B GPTQ	2K / 16.9 GB	2	5
WizardLM 30B Uncensored GPTQ	2K / 16.9 GB	79	118
Tildeopen 30B Mu Instruct	64K / 60.9 GB	41	6
...ct 2048 Open Platypus 100steps	2K / 65.2 GB	88	0
Llama 30B Instruct 2048	2K / 65.2 GB	374	103
...azarus Instruct PL Lora Unload	2K / 65.2 GB	85	0
Llama 30B Instruct	2K / 65.2 GB	333	24
...B 2048 Instruct PL Lora Unload	2K / 65.2 GB	97	1
...lama 30B Instruct 2048 PL Lora	2K / 65.2 GB	89	0
...ge Llama 30B Instruct 2048 AWQ	2K / 17.6 GB	3	2

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/upstage-llama-30b-instruct-2048-GPTQ.