LLM EXPLORER 57,918 MODELS INDEXED

Llama 3.2 90B Vision Instruct Bnb 4bit by unsloth

By unsloth · 361 downloads
HF Repo ↗ Copy URL

Llama 3.2 90B Vision Instruct Bnb 4bit is an open-source language model by unsloth. Features: 90b LLM, VRAM: 49.1GB, License: llama3.2, Quantized, Instruction-Based, LLM Explorer Score: 0.15.

  4-bit   4bit Base model:meta-llama/llama-3.... Base model:quantized:meta-llam...   Bitsandbytes   Conversational   Deploy:azure   En   Endpoints compatible   Facebook   Image-text-to-text   Instruct   Llama   Llama-3   Meta   Mllama   Multimodal   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Unsloth   Vision
Model Card on HF 🤗: https://huggingface.co/unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit 

Llama 3.2 90B Vision Instruct Bnb 4bit Parameters and Internals

LLM NameLlama 3.2 90B Vision Instruct Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit 
Base Model(s)  meta-llama/Llama-3.2-90B-Vision-Instruct   meta-llama/Llama-3.2-90B-Vision-Instruct
Model Size90b
Required VRAM49.1 GB
Updated2026-08-10
Maintainerunsloth
Model Typemllama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-10   5.0 GB: 2-of-10   5.0 GB: 3-of-10   5.0 GB: 4-of-10   4.9 GB: 5-of-10   5.0 GB: 6-of-10   5.0 GB: 7-of-10   5.0 GB: 8-of-10   4.9 GB: 9-of-10   4.3 GB: 10-of-10
Supported Languagesen
Quantization Type4bit
Model ArchitectureMllamaForConditionalGeneration
Licensellama3.2
Model Max Length131072
Transformers Version4.46.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Torch Data Typebfloat16

Best Alternatives to Llama 3.2 90B Vision Instruct Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...a 3.2 90B Vision Instruct 4bit0K / 49.9 GB3184
...sion Instruct Unsloth Bnb 4bit0K / 50.6 GB172
Llama 3.2 90B Vision Instruct0K / 178.2 GB34517
Llama 3.2 90B Vision Instruct0K / 178.2 GB306
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit.