LLM EXPLORER 57,918 MODELS INDEXED

Llama 4 Scout 17B 16E Instruct Unsloth Bnb 4bit by unsloth

By unsloth · 205 downloads
HF Repo ↗ Copy URL

Llama 4 Scout 17B 16E Instruct Unsloth Bnb 4bit is an open-source language model by unsloth. Features: 17b LLM, VRAM: 60.6GB, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.19.

  Arxiv:2204.05149   4-bit   4bit   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   Instruct   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-Instruct-unsloth-bnb-4bit 

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

LLM NameLlama 4 Scout 17B 16E Instruct Unsloth Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit 
Base Model(s)  meta-llama/Llama-4-Scout-17B-16E-Instruct   meta-llama/Llama-4-Scout-17B-16E-Instruct
Model Size17b
Required VRAM60.6 GB
Updated2026-08-10
Maintainerunsloth
Model Typellama4
Instruction-BasedYes
Model Files  5.0 GB: 1-of-13   4.9 GB: 2-of-13   4.9 GB: 3-of-13   5.0 GB: 4-of-13   4.9 GB: 5-of-13   4.9 GB: 6-of-13   5.0 GB: 7-of-13   4.9 GB: 8-of-13   4.9 GB: 9-of-13   5.0 GB: 10-of-13   4.9 GB: 11-of-13   4.2 GB: 12-of-13   2.1 GB: 13-of-13
Supported Languagesar de en es fr hi id it pt th tl vi
Quantization Type4bit
Model ArchitectureLlama4ForConditionalGeneration
Licenseother
Model Max Length10485760
Transformers Version4.51.0
Tokenizer ClassPreTrainedTokenizer
Padding Token<|finetune_right_pad|>
Torch Data Typebfloat16

Best Alternatives to Llama 4 Scout 17B 16E Instruct Unsloth Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...Maverick 17B 16E Instruct 4bit0K / 146.3 GB4197
... 4 Scout 17B 16E Instruct 6bit0K / 88.8 GB3335
...averick 17B 128E Instruct 6bit0K / 201.1 GB1251
... 4 Scout 17B 16E Instruct 4bit0K / 61 GB120312
... 4 Scout 17B 16E Instruct 8bit0K / 114.7 GB5884
...averick 17B 128E Instruct 4bit0K / 140.8 GB2042
...truct Unsloth Dynamic Bnb 4bit0K / 61.7 GB1367
...Maverick 17B 16E Instruct 6bit0K / 213.8 GB1312
... 16E Instruct Unsloth Bnb 8bit0K / 111.5 GB229
... 4 Scout 17B 16E Instruct GGUF0K / 1.8 GB34225163
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit.