LLM EXPLORER 57,918 MODELS INDEXED

Llama 4 Maverick 17B 128E Instruct by unsloth

By unsloth · 3508 downloads
HF Repo ↗ Copy URL

Llama 4 Maverick 17B 128E Instruct is an open-source language model by unsloth. Features: 17b LLM, VRAM: 631.8GB, License: other, Instruction-Based, LLM Explorer Score: 0.2.

  Arxiv:2204.05149   Ar Base model:finetune:meta-llama... Base model:meta-llama/llama-4-...   Conversational   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   Id   Image-text-to-text   Instruct   It   Llama   Llama4   Meta   Pt   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Th   Tl   Unsloth   Vi
Model Card on HF 🤗: https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct 

Llama 4 Maverick 17B 128E Instruct Parameters and Internals

LLM NameLlama 4 Maverick 17B 128E Instruct
Repository 🤗https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct 
Base Model(s)  meta-llama/Llama-4-Maverick-17B-128E-Instruct   meta-llama/Llama-4-Maverick-17B-128E-Instruct
Model Size17b
Required VRAM631.8 GB
Updated2026-08-10
Maintainerunsloth
Model Typellama4
Instruction-BasedYes
Model Files  21.5 GB: 1-of-55   10.7 GB: 2-of-55   5.0 GB: 3-of-55   21.5 GB: 4-of-55   10.7 GB: 5-of-55   21.5 GB: 6-of-55   10.7 GB: 7-of-55   21.5 GB: 8-of-55   10.7 GB: 9-of-55   21.5 GB: 10-of-55   10.7 GB: 11-of-55   21.5 GB: 12-of-55   10.7 GB: 13-of-55   5.0 GB: 14-of-55   21.5 GB: 15-of-55   10.7 GB: 16-of-55   21.5 GB: 17-of-55   10.7 GB: 18-of-55   21.5 GB: 19-of-55   10.7 GB: 20-of-55   21.5 GB: 21-of-55   10.7 GB: 22-of-55   21.5 GB: 23-of-55   10.7 GB: 24-of-55   5.0 GB: 25-of-55   21.5 GB: 26-of-55   10.7 GB: 27-of-55   21.5 GB: 28-of-55   10.7 GB: 29-of-55   21.5 GB: 30-of-55   10.7 GB: 31-of-55   21.5 GB: 32-of-55   10.7 GB: 33-of-55   21.5 GB: 34-of-55   10.7 GB: 35-of-55   5.0 GB: 36-of-55   21.5 GB: 37-of-55   10.7 GB: 38-of-55   21.5 GB: 39-of-55   10.7 GB: 40-of-55   21.5 GB: 41-of-55   10.7 GB: 42-of-55
Supported Languagesar de en es fr hi id it pt th tl vi
Model ArchitectureLlama4ForConditionalGeneration
Licenseother
Transformers Version4.52.4
Torch Data Typebfloat16

Best Alternatives to Llama 4 Maverick 17B 128E Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Llama 4 Scout 17B 16E Instruct0K / 188.7 GB358657
...Maverick 17B 128E Instruct FP80K / 210 GB7296
...Scout 17B 16E Instruct Unsloth0K / 197.5 GB2317
...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
... 16E Instruct Unsloth Bnb 4bit0K / 60.6 GB20580
... 4 Scout 17B 16E Instruct 8bit0K / 114.7 GB5884
...averick 17B 128E Instruct 4bit0K / 140.8 GB2042
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Llama-4-Maverick-17B-128E-Instruct.