LLM EXPLORER 64,206 MODELS INDEXED

AesCode 8B by microsoft

By microsoft · 356 downloads
HF Repo ↗ Copy URL

AesCode 8B is an open-source language model by microsoft. Features: 8b LLM, VRAM: 17.5GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.36.

  Arxiv:2610.18860 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-8b-in...   Code-generation   Conversational   Design   En   Endpoints compatible   Html   Image-text-to-text   Instruct   Multimodal   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/microsoft/AesCode-8B 

AesCode 8B Parameters and Internals

LLM NameAesCode 8B
Repository 🤗https://huggingface.co/microsoft/AesCode-8B 
Base Model(s)  Qwen3 VL 8B Instruct   Qwen/Qwen3-VL-8B-Instruct
Model Size8b
Required VRAM17.5 GB
Updated2026-10-14
Maintainermicrosoft
Model Typeqwen3_vl
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   2.6 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.6
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to AesCode 8B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 8B Instruct0K / 17.5 GB44943291037
Qwen3 VL 8B Instruct FP80K / 10.6 GB310860477
Qwen3vl Resume Parser0K / 17.5 GB2574553
PhysBrain1.5 8B0K / 17.8 GB63827
Qwen3 VL 8B Heretic 1.3.00K / 17.5 GB465312
Uzocr 8B0K / 17.5 GB661
Qwen3 VL 8B CrossImage SFT0K / 17.5 GB440
ArmorOCR0K / 17.5 GB1959
Video HopChain 8B Standard RL0K / 17.6 GB530
Qwen3 VL 8B VQA SFT0K / 17.5 GB1990
Note: green Score (e.g. "73.2") means that the model is better than microsoft/AesCode-8B.