LLM EXPLORER 57,918 MODELS INDEXED

CapRL Eval 3B by internlm

By internlm · 87 downloads

CapRL Eval 3B is an open-source language model by internlm. Features: 3b LLM, VRAM: 7.5GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.

  Arxiv:2509.22647   Conversational   Endpoints compatible   Image-text-to-text   Instruct   Qwen2 5 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF πŸ€—: https://huggingface.co/internlm/CapRL-Eval-3B 

CapRL Eval 3B Parameters and Internals

LLM NameCapRL Eval 3B
Repository πŸ€—https://huggingface.co/internlm/CapRL-Eval-3B 
Model Size3b
Required VRAM7.5 GB
Updated2026-08-10
Maintainerinternlm
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.5 GB: 2-of-2
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licenseapache-2.0
Context Length128000
Model Max Length128000
Transformers Version4.49.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to CapRL Eval 3B

Best Alternatives
Context / RAM
Downloads
Likes
Nanonets OCR2 3B125K / 7.5 GB659329511
Qwen2.5 VL 3B Instruct125K / 7.5 GB7336490683
Nanonets OCR S125K / 7.5 GB521511591
Typhoon Ocr 3B125K / 7.5 GB3569139
Spatial SSRL 3B125K / 8.2 GB1617
NV Reason CXR 3B125K / 8.1 GB90031
CapRL 3B125K / 7.5 GB23047
ScaleCUA 3B125K / 7.5 GB26113
Nanonets OCR S Bf16125K / 7.5 GB962
Qwen2.5 VL 3B Instruct125K / 7.5 GB27106
Note: green Score (e.g. "73.2") means that the model is better than internlm/CapRL-Eval-3B.