LLM EXPLORER 58,178 MODELS INDEXED

InSight Doc 8B by InSight-doc

By InSight-doc · 90 downloads
HF Repo ↗ Copy URL

InSight Doc 8B is an open-source language model by InSight-doc. Features: 8b LLM, VRAM: 17.6GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.29.

  Arxiv:2608.10628   Agentic-ai Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-8b-in...   Conversational Dataset:m-just/insight-doc-rl-... Dataset:m-just/insight-doc-sft...   Document-vqa   En   Endpoints compatible   Image-text-to-text   Instruct   Long-document-understanding   Qwen3-vl   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow   Tool-use   Vision   Vision-language   Visual-question-answering
Model Card on HF 🤗: https://huggingface.co/InSight-doc/InSight-doc-8B 

InSight Doc 8B Parameters and Internals

LLM NameInSight Doc 8B
Repository 🤗https://huggingface.co/InSight-doc/InSight-doc-8B 
Base Model(s)  Qwen3 VL 8B Instruct   Qwen/Qwen3-VL-8B-Instruct
Model Size8b
Required VRAM17.6 GB
Updated2026-08-12
MaintainerInSight-doc
Model Typeqwen3_vl
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   2.7 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 InSight Doc 8B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 8B Instruct0K / 17.5 GB44943291037
Qwen3 VL 8B Instruct FP80K / 10.6 GB310860477
Qwen3 VL 8B Heretic 1.3.00K / 17.5 GB465312
Zhimu 1.00K / 18.6 GB291
RefCaptioner0K / 17.5 GB611
ZwZ 8B0K / 17.6 GB258648
... Simple Path Dense S100 Step900K / 17.5 GB131
Qwen3 VL 8B Instruct0K / 17.5 GB542810
Qwen3 VL 8B Instruct FP80K / 10.6 GB10677
Qwen3 VL 8B Instruct Bf160K / 17.6 GB1273
Note: green Score (e.g. "73.2") means that the model is better than InSight-doc/InSight-doc-8B.