LLM EXPLORER 55,709 MODELS INDEXED

Llama 4 Scout 17B 16E 4bit by mlx-community

By mlx-community · 163 downloads
HF Repo ↗ Copy URL

Llama 4 Scout 17B 16E 4bit is an open-source language model by mlx-community. Features: 17b LLM, VRAM: 61GB, License: other, Quantized.

  4bit   Ar   Conversational   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   Id   Image-text-to-text   It   Llama   Llama-4   Llama4   Meta   Mlx   Pt   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Th   Tl   Vi
Model Card on HF 🤗: https://huggingface.co/mlx-community/Llama-4-Scout-17B-16E-4bit 

Llama 4 Scout 17B 16E 4bit Parameters and Internals

LLM NameLlama 4 Scout 17B 16E 4bit
Repository 🤗https://huggingface.co/mlx-community/Llama-4-Scout-17B-16E-4bit 
Model Size17b
Required VRAM61 GB
Updated2026-08-08
Maintainermlx-community
Model Typellama4
Model Files  5.2 GB: 1-of-12   5.3 GB: 2-of-12   5.4 GB: 3-of-12   5.0 GB: 4-of-12   5.3 GB: 5-of-12   5.3 GB: 6-of-12   5.4 GB: 7-of-12   5.0 GB: 8-of-12   5.3 GB: 9-of-12   5.3 GB: 10-of-12   5.4 GB: 11-of-12   3.1 GB: 12-of-12
Supported Languagesar de en es fr hi id it pt th tl vi
Quantization Type4bit
Model ArchitectureLlama4ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version4.51.0
Padding Token<|finetune_right_pad_id|>

Best Alternatives to Llama 4 Scout 17B 16E 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...Maverick 17B 16E Instruct 4bit0K / 146.3 GB4197
...ama Llama 4 Scout 17B 16E 4bit0K / 60.5 GB3388
...ama Llama 4 Scout 17B 16E Fp160K / 207.3 GB1522
...Maverick 17B 16E Instruct 6bit0K / 213.8 GB1312
... 4 Scout 17B 16E Instruct 4bit0K / 61 GB120312
... 4 Scout 17B 16E Instruct 6bit0K / 88.8 GB3335
... 4 Scout 17B 16E Instruct 8bit0K / 114.7 GB5884
...averick 17B 128E Instruct 4bit0K / 140.8 GB2042
...averick 17B 128E Instruct 6bit0K / 201.1 GB1251
...ama Llama 4 Scout 17B 16E Bf160K / 207.3 GB7902
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Llama-4-Scout-17B-16E-4bit.