What are the hardware requirements for Llama 4 Scout 17B 16E Unsloth Bnb 8bit?

Llama 4 Scout 17B 16E Unsloth Bnb 8bit requires approximately 111.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 4 Scout 17B 16E Unsloth Bnb 8bit and how large is it?

Llama 4 Scout 17B 16E Unsloth Bnb 8bit is developed by unsloth, a model with 17b 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 Llama 4 Scout 17B 16E Unsloth Bnb 8bit?

Llama 4 Scout 17B 16E Unsloth Bnb 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 4 Scout 17B 16E Unsloth Bnb 8bit by unsloth — VRAM 111.5GB

Name: Llama 4 Scout 17B 16E Unsloth Bnb 8bit
Author: unsloth

Llama 4 Scout 17B 16E Unsloth Bnb 8bit is an open-source language model by unsloth. Features: 17b LLM, VRAM: 111.5GB, License: other, Quantized, LLM Explorer Score: 0.18.

Arxiv:2204.05149 8-bit 8bit Ar Base model:meta-llama/llama-4-... Base model:quantized:meta-llam... Bitsandbytes Conversational De En Endpoints compatible Es Facebook Fr Hi Id Image-text-to-text It Llama Llama-4 Llama4 Meta Pt Pytorch Quantized Region:us Safetensors Sharded Tensorflow Th Tl Vi

Model Card on HF 🤗: https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-unsloth-bnb-8bit

Llama 4 Scout 17B 16E Unsloth Bnb 8bit Parameters and Internals

LLM Name	Llama 4 Scout 17B 16E Unsloth Bnb 8bit
Repository 🤗	https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-unsloth-bnb-8bit
Base Model(s)	meta-llama/Llama-4-Scout-17B-16E meta-llama/Llama-4-Scout-17B-16E
Model Size	17b
Required VRAM	111.5 GB
Updated	2026-08-10
Maintainer	unsloth
Model Type	llama4
Model Files	4.5 GB: 1-of-26 4.4 GB: 2-of-26 4.4 GB: 3-of-26 4.4 GB: 4-of-26 4.4 GB: 5-of-26 4.4 GB: 6-of-26 4.4 GB: 7-of-26 4.4 GB: 8-of-26 4.4 GB: 9-of-26 4.4 GB: 10-of-26 4.4 GB: 11-of-26 4.4 GB: 12-of-26 4.4 GB: 13-of-26 4.4 GB: 14-of-26 4.4 GB: 15-of-26 4.4 GB: 16-of-26 4.4 GB: 17-of-26 4.4 GB: 18-of-26 4.4 GB: 19-of-26 4.4 GB: 20-of-26 4.4 GB: 21-of-26 4.4 GB: 22-of-26 4.4 GB: 23-of-26 4.4 GB: 24-of-26 3.7 GB: 25-of-26 2.1 GB: 26-of-26
Supported Languages	ar de en es fr hi id it pt th tl vi
Quantization Type	8bit
Model Architecture	Llama4ForConditionalGeneration
License	other
Model Max Length	262144
Transformers Version	4.51.0
Tokenizer Class	PreTrainedTokenizer
Padding Token	<\|finetune_right_pad_id\|>
Torch Data Type	bfloat16

Rank the Llama 4 Scout 17B 16E Unsloth Bnb 8bit 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 Llama 4 Scout 17B 16E Unsloth Bnb 8bit

Best Alternatives	Context / RAM	Downloads	Likes
...Maverick 17B 16E Instruct 4bit	0K / 146.3 GB	419	7
... 4 Scout 17B 16E Instruct 6bit	0K / 88.8 GB	333	5
...averick 17B 128E Instruct 6bit	0K / 201.1 GB	125	1
... 4 Scout 17B 16E Instruct 4bit	0K / 61 GB	1203	12
... 16E Instruct Unsloth Bnb 4bit	0K / 60.6 GB	205	80
... 4 Scout 17B 16E Instruct 8bit	0K / 114.7 GB	588	4
...Scout 17B 16E Unsloth Bnb 4bit	0K / 60.6 GB	562	5
...ama Llama 4 Scout 17B 16E 4bit	0K / 60.5 GB	338	8
...averick 17B 128E Instruct 4bit	0K / 140.8 GB	204	2
Llama 4 Scout 17B 16E 4bit	0K / 61 GB	163	2

Note: green Score (e.g. "73.2") means that the model is better than unsloth/Llama-4-Scout-17B-16E-unsloth-bnb-8bit.