LLM EXPLORER 62,939 MODELS INDEXED

Madrimed1.2 VL 2B by madrisight

By madrisight · 44 downloads
HF Repo ↗ Copy URL

Madrimed1.2 VL 2B is an open-source language model by madrisight. Features: 2b LLM, VRAM: 9.8GB, License: apache-2.0, LLM Explorer Score: 0.29.

  2b Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-2b-th...   Clinical-reasoning   Conversational   En   Endpoints compatible   Grpo   Image-text-to-text   Medical   Medmcqa   Medxpertqa   Multimodal   Path-vqa   Pathology   Qwen3-vl   Qwen3 vl   Radiology   Region:us   Rlhf   Safetensors   Sharded   Slake   Tensorflow   Vision   Vision-language   Vqa-rad
Model Card on HF 🤗: https://huggingface.co/madrisight/madrimed1.2-VL-2B 

Madrimed1.2 VL 2B Parameters and Internals

LLM NameMadrimed1.2 VL 2B
Repository 🤗https://huggingface.co/madrisight/madrimed1.2-VL-2B 
Base Model(s)  Qwen3 VL 2B Thinking   Qwen/Qwen3-VL-2B-Thinking
Model Size2b
Required VRAM9.8 GB
Updated2026-10-04
Maintainermadrisight
Model Typeqwen3_vl
Model Files  1.2 GB: 1-of-6   2.0 GB: 2-of-6   2.0 GB: 3-of-6   2.0 GB: 4-of-6   2.0 GB: 5-of-6   0.6 GB: 6-of-6
Supported Languagesen
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.11.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Madrimed1.2 VL 2B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 2B Instruct0K / 4.3 GB2204577448
Qwen3 VL Reranker 2B0K / 4.3 GB764323212
WeVisDoc 2B0K / 4.9 GB59914
PhysBrain1.5 2B0K / 4.3 GB27213
Qwen3 VL 2B Thinking0K / 4.3 GB74744115
Qevi 2B0K / 4.3 GB612
Qwen3 VL 2B Instruct FP80K / 3.5 GB6506343
Typhoon Ocr1.5 2B0K / 4.3 GB5502925
VQS0K / 4.3 GB261
Foresight Qwen3vl 2B Sft0K / 4.3 GB541
Note: green Score (e.g. "73.2") means that the model is better than madrisight/madrimed1.2-VL-2B.