LLM EXPLORER 67,627 MODELS INDEXED

Grpo Qwen3 Vl 4B Thinking by posterior-learning

By posterior-learning · 27 downloads

Grpo Qwen3 Vl 4B Thinking is an open-source language model by posterior-learning. Features: 4b LLM, VRAM: 8.9GB, Merged, LLM Explorer Score: 0.29.

  Merged Model Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-4b-th...   Conversational   Endpoints compatible   Image-text-to-text   Posterior-learning   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow

Grpo Qwen3 Vl 4B Thinking Parameters and Internals

LLM NameGrpo Qwen3 Vl 4B Thinking
Repository πŸ€—https://huggingface.co/posterior-learning/grpo-qwen3-vl-4b-thinking 
Base Model(s)  Qwen3 VL 4B Thinking   Qwen/Qwen3-VL-4B-Thinking
Merged ModelYes
Model Size4b
Required VRAM8.9 GB
Updated2026-11-16
Maintainerposterior-learning
Model Typeqwen3_vl
Model Files  5.0 GB: 1-of-2   3.9 GB: 2-of-2
Model ArchitectureQwen3VLForConditionalGeneration
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Grpo Qwen3 Vl 4B Thinking

Best Alternatives
Context / RAM
Downloads
Likes
WeVisOne VL 4B0K / 19.3 GB260558
Qwen3 VL 4B Instruct0K / 8.9 GB3611570437
FemboyAV 4B0K / 8.9 GB7570
MinerU Popo0K / 17.6 GB268954
Qwen3 VL 4B Instruct FP80K / 6.1 GB30110365
...ft Belief Qwen3 Vl 4B Thinking0K / 8.9 GB291
Qwen3 VL 4B Thinking Pashto Zi0K / 8.9 GB14260
WeVisDoc 4B0K / 9.7 GB34931
UAV PUR 4B0K / 8.9 GB221
VIG Qwen3 VL Thinking 4B0K / 9.7 GB481
Note: green Score (e.g. "73.2") means that the model is better than posterior-learning/grpo-qwen3-vl-4b-thinking.