What are the hardware requirements for Meta Llama 3 8B Instruct 64K AWQ?

Meta Llama 3 8B Instruct 64K AWQ requires approximately 5.8 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Meta Llama 3 8B Instruct 64K AWQ and how large is it?

Meta Llama 3 8B Instruct 64K AWQ is developed by heyholetsgo, 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 64K AWQ perform on standard benchmarks?

Meta Llama 3 8B Instruct 64K AWQ 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 64K AWQ by heyholetsgo — VRAM 5.8GB, 64K context

Name: Meta Llama 3 8B Instruct 64K AWQ
Author: heyholetsgo

Meta Llama 3 8B Instruct 64K AWQ is an open-source language model by heyholetsgo. Features: 8b LLM, VRAM: 5.8GB, Context: 64K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.13, Arc: 59.9, HellaSwag: 80, MMLU: 64.8, GSM8K: 65.7.

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

Model Card on HF 🤗: https://huggingface.co/heyholetsgo/Meta-Llama-3-8B-Instruct-64k-awq

Meta Llama 3 8B Instruct 64K AWQ Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

commercial, research

Applications:

natural language generation tasks

Primary Use Cases:

assistant-like chat, custom tuning

Limitations:

Use only in English, Must comply with License and Acceptable Use Policy

Considerations:

Developers may fine-tune for languages beyond English if compliant with License and Acceptable Use Policy.

Supported Languages

English (Proficient)

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

Hardware Used:

Meta's Research SuperCluster, third-party cloud compute

Model Architecture:

optimized transformer architecture

Responsible Ai Considerations

Mitigation Strategies:

Safety mitigations techniques and responsible LLM-application deployment guidelines.

Input Output

Input Format:

text

Accepted Modalities:

text

Output Format:

text, code

Release Notes

Version:

Date:

2024-04-18

Notes:

Llama 3 released with improvements in helpfulness and safety.

LLM Name	Meta Llama 3 8B Instruct 64K AWQ
Repository 🤗	https://huggingface.co/heyholetsgo/Meta-Llama-3-8B-Instruct-64k-awq
Base Model(s)	...a Llama 3 8B Instruct 64K PoSE Azma-AI/Meta-Llama-3-8B-Instruct-64k-PoSE
Model Size	8b
Required VRAM	5.8 GB
Updated	2026-08-06
Maintainer	heyholetsgo
Model Type	llama
Instruction-Based	Yes
Model Files	4.7 GB: 1-of-2 1.1 GB: 2-of-2
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	other
Context Length	65536
Model Max Length	65536
Transformers Version	4.37.2
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	float16

Rank the Meta Llama 3 8B Instruct 64K AWQ 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 64K AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...8B Instruct Gradient 1048K AWQ	1024K / 5.8 GB	8	0
...radient 1048K AWQ 4bit Smashed	1024K / 5.8 GB	7	1
...Instruct 262K AWQ 4bit Smashed	256K / 5.8 GB	5	4
... Instruct 8B 32K V0.1 4bit AWQ	64K / 5.8 GB	9	0
Llama 3 8B Instruct AWQ	8K / 5.8 GB	25458	31
Meta Llama 3 8B Instruct AWQ	8K / 5.8 GB	6	0
Meta Llama 3 8B Instruct AWQ	8K / 5.8 GB	563	0
Meta Llama 3 8B Instruct AWQ	8K / 5.8 GB	7	0
Meta Llama 3 8B Instruct AWQ	8K / 5.8 GB	401	5
...eta Llama 3 8B Instruct Hf AWQ	8K / 5.8 GB	179	9

Note: green Score (e.g. "73.2") means that the model is better than heyholetsgo/Meta-Llama-3-8B-Instruct-64k-awq.