What are the hardware requirements for Meta Llama 3 8B Instruct GPTQ?

Meta Llama 3 8B Instruct GPTQ requires approximately 5.8 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Meta Llama 3 8B Instruct GPTQ and how large is it?

Meta Llama 3 8B Instruct GPTQ is developed by SalmanFaroz, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Meta Llama 3 8B Instruct GPTQ perform on standard benchmarks?

Meta Llama 3 8B Instruct GPTQ has the following published scores: MMLU 64.8. Compare against reference models on this page or on the LLM Explorer leaderboards.

Meta Llama 3 8B Instruct GPTQ by SalmanFaroz — VRAM 5.8GB, 8K context

Name: Meta Llama 3 8B Instruct GPTQ
Author: SalmanFaroz

Meta Llama 3 8B Instruct GPTQ is an open-source language model by SalmanFaroz. Features: 8b LLM, VRAM: 5.8GB, Context: 8K, License: llama3, Quantized, Instruction-Based, LLM Explorer Score: 0.14, Arc: 59.9, HellaSwag: 80, MMLU: 64.8, GSM8K: 65.7.

4-bit Conversational En Endpoints compatible Facebook Gptq Instruct Llama Llama-3 Meta Pytorch Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/SalmanFaroz/Meta-Llama-3-8B-Instruct-GPTQ

Meta Llama 3 8B Instruct GPTQ Parameters and Internals

Model Type

text generation

Use Cases

Areas:

commercial, research

Applications:

assistant-like chat

Primary Use Cases:

instruction tuned models for chat

Limitations:

Use in languages other than English, Complies with Acceptable Use Policy

Additional Notes

Static model trained on an offline dataset with plans for future updates.

Supported Languages

English (primary)

Training Details

Data Sources:

publicly available online data

Data Volume:

15T+ tokens

Methodology:

supervised fine-tuning and reinforcement learning with human feedback

Context Length:

8000

Model Architecture:

auto-regressive language model with an optimized transformer architecture

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text and code

LLM Name	Meta Llama 3 8B Instruct GPTQ
Repository 🤗	https://huggingface.co/SalmanFaroz/Meta-Llama-3-8B-Instruct-GPTQ
Base Model(s)	...eta Llama 3 8B Instruct FP8 KV neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV
Model Size	8b
Required VRAM	5.8 GB
Updated	2026-06-01
Maintainer	SalmanFaroz
Model Type	llama
Instruction-Based	Yes
Model Files	4.7 GB: 1-of-2 1.1 GB: 2-of-2
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Transformers Version	4.41.1
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	float16

Rank the Meta Llama 3 8B Instruct 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 Meta Llama 3 8B Instruct GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...a 3 8B Instruct 262K 4bit GPTQ	256K / 5.8 GB	5	1
... 8B Instruct 262K 4bit GPTQ 02	256K / 5.7 GB	6	0
...Instruct V0.5 GPTQ Safetensors	128K / 4.9 GB	113	0
...lama 3.1 8B Instruct GPTQ INT4	128K / 5.8 GB	9169	42
...Instruct 80K Qlora Merged GPTQ	80K / 5.8 GB	6	0
...oLeo Instruct 8B 32K V0.1 GPTQ	64K / 5.7 GB	5	0
Meta Llama 3 8B Instruct GPTQ	8K / 5.8 GB	6	0
...ta Llama 3 8B Instruct GPTQ 8B	8K / 9.2 GB	7	0
Meta Llama 3 8B Instruct GPTQ	8K / 5.7 GB	2895	7
...truct Abliterated V3 GPTQ 4bit	8K / 5.8 GB	9	0

Note: green Score (e.g. "73.2") means that the model is better than SalmanFaroz/Meta-Llama-3-8B-Instruct-GPTQ.