LLM EXPLORER 59,358 MODELS INDEXED

EXAONE 4.0 32B 4bit by mlx-community

By mlx-community · 87 downloads
HF Repo ↗ Copy URL

EXAONE 4.0 32B 4bit is an open-source language model by mlx-community. Features: 32b LLM, VRAM: 18GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.19.

  4-bit   4bit Base model:lgai-exaone/exaone-... Base model:quantized:lgai-exao...   Conversational   En   Es   Exaone   Exaone-4.0   Exaone4   Ko   Lg-ai   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/EXAONE-4.0-32B-4bit 

EXAONE 4.0 32B 4bit Parameters and Internals

LLM NameEXAONE 4.0 32B 4bit
Repository 🤗https://huggingface.co/mlx-community/EXAONE-4.0-32B-4bit 
Base Model(s)  LGAI-EXAONE/EXAONE-4.0-32B   LGAI-EXAONE/EXAONE-4.0-32B
Model Size32b
Required VRAM18 GB
Updated2026-07-04
Maintainermlx-community
Model Typeexaone4
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.3 GB: 3-of-4   2.0 GB: 4-of-4
Supported Languagesen ko es
Quantization Type4bit
Model ArchitectureExaone4ForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.54.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token[PAD]
Vocabulary Size102400
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to EXAONE 4.0 32B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
EXAONE 4.0 32B128K / 63.7 GB24028281
EXAONE 4.0.1 32B128K / 63.7 GB593827
EXAONE 4.0 32B128K / 63.7 GB122
...hui EXAONE 4.0 32B Abliterated128K / 63.7 GB1660
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/EXAONE-4.0-32B-4bit.