LLM EXPLORER 58,531 MODELS INDEXED

A.X 4.0 Light MLX BF16 by mlx-community

By mlx-community · 5 downloads
HF Repo ↗ Copy URL

A.X 4.0 Light MLX BF16 is an open-source language model by mlx-community. Features: 7b LLM, VRAM: 14.5GB, Context: 16K, License: apache-2.0, LLM Explorer Score: 0.22.

Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2.5-7b   Conversational   En   Ko   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/A.X-4.0-Light-MLX-BF16 

A.X 4.0 Light MLX BF16 Parameters and Internals

LLM NameA.X 4.0 Light MLX BF16
Repository 🤗https://huggingface.co/mlx-community/A.X-4.0-Light-MLX-BF16 
Base Model(s)  Qwen/Qwen2.5-7B   Qwen/Qwen2.5-7B
Model Size7b
Required VRAM14.5 GB
Updated2026-08-10
Maintainermlx-community
Model Typeqwen2
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   3.9 GB: 3-of-3
Supported Languagesen ko
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.51.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|pad|>
Vocabulary Size102400
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to A.X 4.0 Light MLX BF16

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Preview986K / 15.2 GB100
Qwen2.5 7B Instruct 1M986K / 15.4 GB52534373
Hush Qwen2.5 7B V1.2986K / 15.2 GB41
Hush Qwen2.5 7B V1.1986K / 15.2 GB51
Hush Qwen2.5 7B V1.4986K / 15.2 GB81
Hush Qwen2.5 7B Preview986K / 15.2 GB50
Hush Qwen2.5 7B V1.3986K / 15.2 GB102
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB102
Qwen 2.5 7B Exp Sce986K / 15.2 GB102
Qwen2.5 7B MixStock V0.1986K / 15.2 GB63
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/A.X-4.0-Light-MLX-BF16.