LLM EXPLORER 55,709 MODELS INDEXED

Llama 3.2 11B Vision Instruct 8bit by mlx-community

By mlx-community · 1272 downloads
HF Repo ↗ Copy URL

Llama 3.2 11B Vision Instruct 8bit is an open-source language model by mlx-community. Features: 11b LLM, VRAM: 11.4GB, License: llama3.2, Quantized, Instruction-Based.

  8bit Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational   Deploy:azure   En   Endpoints compatible   Facebook   Image-text-to-text   Instruct   Llama   Llama-3   Meta   Mllama   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Unsloth   Vision
Model Card on HF 🤗: https://huggingface.co/mlx-community/Llama-3.2-11B-Vision-Instruct-8bit 

Llama 3.2 11B Vision Instruct 8bit Parameters and Internals

LLM NameLlama 3.2 11B Vision Instruct 8bit
Repository 🤗https://huggingface.co/mlx-community/Llama-3.2-11B-Vision-Instruct-8bit 
Base Model(s)  meta-llama/Llama-3.2-11B-Vision-Instruct   meta-llama/Llama-3.2-11B-Vision-Instruct
Model Size11b
Required VRAM11.4 GB
Updated2026-08-08
Maintainermlx-community
Model Typemllama
Instruction-BasedYes
Model Files  5.4 GB: 1-of-3   5.3 GB: 2-of-3   0.7 GB: 3-of-3
Supported Languagesen
Quantization Type8bit
Model ArchitectureMllamaForConditionalGeneration
Licensellama3.2
Model Max Length131072
Transformers Version4.45.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Torch Data Typebfloat16

Best Alternatives to Llama 3.2 11B Vision Instruct 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...a 3.2 11B Vision Instruct 4bit0K / 6 GB9027
...1B Vision Instruct FP8 Dynamic0K / 12.6 GB449022
...1B Vision Instruct FP8 Dynamic0K / 12.6 GB144224
...ion Instruct Abliterated 4 Bit0K / 6 GB3121
...ion Instruct Abliterated 8 Bit0K / 11.4 GB1521
...1B Vision Instruct Abliterated0K / 21.3 GB8137
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Llama-3.2-11B-Vision-Instruct-8bit.