LLM EXPLORER 60,897 MODELS INDEXED

Ling 3.0 Flash VL Fp8 by inclusionAI

By inclusionAI · 465 downloads
HF Repo ↗ Copy URL

Ling 3.0 Flash VL Fp8 is an open-source language model by inclusionAI. Features: 124.8b LLM, VRAM: 77.6GB, License: mit, MoE, LLM Explorer Score: 0.38.

  Bailing moe v3 vl   Conversational   Custom code   Fp8   Image-text-to-text   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/inclusionAI/Ling-3.0-flash-VL-fp8 

Ling 3.0 Flash VL Fp8 Parameters and Internals

LLM NameLing 3.0 Flash VL Fp8
Repository 🤗https://huggingface.co/inclusionAI/Ling-3.0-flash-VL-fp8 
Model Size124.8b
Required VRAM77.6 GB
Updated2026-09-11
MaintainerinclusionAI
Model Typebailing_moe_v3_vl
Model Files  3.7 GB: 0-of-64   1.5 GB: 1-of-64   1.5 GB: 2-of-64   1.5 GB: 3-of-64   1.5 GB: 4-of-64   1.5 GB: 5-of-64   1.5 GB: 6-of-64   1.5 GB: 7-of-64   2.7 GB: 8-of-64   2.3 GB: 9-of-64   2.3 GB: 10-of-64   2.3 GB: 11-of-64   2.3 GB: 12-of-64   2.3 GB: 13-of-64   2.3 GB: 14-of-64   2.3 GB: 15-of-64   2.2 GB: 16-of-64   1.9 GB: 17-of-64   1.9 GB: 18-of-64   1.9 GB: 19-of-64   1.9 GB: 20-of-64   1.9 GB: 21-of-64   1.9 GB: 22-of-64   1.9 GB: 23-of-64   2.2 GB: 24-of-64   1.9 GB: 25-of-64   1.9 GB: 26-of-64   1.9 GB: 27-of-64   1.9 GB: 28-of-64   1.9 GB: 29-of-64   1.9 GB: 30-of-64   1.9 GB: 31-of-64   2.2 GB: 32-of-64   1.9 GB: 33-of-64   1.9 GB: 34-of-64   1.9 GB: 35-of-64   1.9 GB: 36-of-64   1.9 GB: 37-of-64   1.9 GB: 38-of-64
Model ArchitectureBailingMoeV3VLForConditionalGeneration
Licensemit
Transformers Version4.56.2
Torch Data Typebfloat16

Best Alternatives to Ling 3.0 Flash VL Fp8

Best Alternatives
Context / RAM
Downloads
Likes
Ling 3.0 Flash VL Int40K / 47.5 GB50818
Ling 3.0 Flash VL0K / 152.7 GB4237