LLM EXPLORER 60,519 MODELS INDEXED

Ling 2.6 Flash Mlx 4bit Gs32 by mlx-community

By mlx-community · 22 downloads
HF Repo ↗ Copy URL

Ling 2.6 Flash Mlx 4bit Gs32 is an open-source language model by mlx-community. Features: 104.2b LLM, VRAM: 65.2GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.23.

  4-bit   4bit   Bailing hybrid Base model:inclusionai/ling-2.... Base model:quantized:inclusion...   Conversational   Custom code   En   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Ling-2.6-flash-mlx-4bit-gs32 

Ling 2.6 Flash Mlx 4bit Gs32 Parameters and Internals

LLM NameLing 2.6 Flash Mlx 4bit Gs32
Repository 🤗https://huggingface.co/mlx-community/Ling-2.6-flash-mlx-4bit-gs32 
Base Model(s)  inclusionAI/Ling-2.6-flash   inclusionAI/Ling-2.6-flash
Model Size104.2b
Required VRAM65.2 GB
Updated2026-07-27
Maintainermlx-community
Model Typebailing_hybrid
Model Files  5.3 GB: 1-of-13   4.9 GB: 2-of-13   4.8 GB: 3-of-13   5.4 GB: 4-of-13   5.0 GB: 5-of-13   5.3 GB: 6-of-13   5.0 GB: 7-of-13   5.4 GB: 8-of-13   5.0 GB: 9-of-13   5.4 GB: 10-of-13   5.0 GB: 11-of-13   5.4 GB: 12-of-13   3.3 GB: 13-of-13
Supported Languagesen
Quantization Type4bit
Model ArchitectureBailingMoeV2_5ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.56.2
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size157184
Torch Data Typebfloat16

Best Alternatives to Ling 2.6 Flash Mlx 4bit Gs32

Best Alternatives
Context / RAM
Downloads
Likes
Ling 2.6 Flash Mlx 8bit128K / 111.2 GB691
Ling 2.6 Flash Mlx 5bit128K / 71.6 GB451
Ling 2.6 Flash Mlx 6bit128K / 85 GB361
Ling 2.6 Flash Mlx 4bit DWQ128K / 58.6 GB827
Ling 2.6 Flash Mlx 4bit128K / 58.6 GB682
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Ling-2.6-flash-mlx-4bit-gs32.