ScaleCUA 3B is an open-source language model by OpenGVLab. Features: 3b LLM, VRAM: 7.5GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.
| LLM Name | ScaleCUA 3B |
| Repository 🤗 | https://huggingface.co/OpenGVLab/ScaleCUA-3B |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 7.5 GB |
| Updated | 2026-08-08 |
| Maintainer | OpenGVLab |
| Model Type | qwen2_5_vl |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2_5_VLForConditionalGeneration |
| License | apache-2.0 |
| Context Length | 128000 |
| Model Max Length | 128000 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Nanonets OCR2 3B | 125K / 7.5 GB | 659329 | 511 |
| Qwen2.5 VL 3B Instruct | 125K / 7.5 GB | 2710 | 6 |
| Nanonets OCR S Bf16 | 125K / 7.5 GB | 96 | 2 |
| ...2.5 VL 3B Instruct Abliterated | 125K / 7.5 GB | 50 | 1 |
| Qwen2.5 VL 3B Instruct Bf16 | 125K / 7.5 GB | 155 | 4 |
| Nanonets OCR2 3B 8bit | 125K / 4.6 GB | 103 | 1 |
| Qwen2.5 VL 3B Instruct 4bit | 125K / 3.1 GB | 3235 | 5 |
| Holo1 3B 4bit | 125K / 3.1 GB | 27 | 1 |
| Holo1 3B 3bit | 125K / 2.7 GB | 21 | 1 |
| Qwen2.5 VL 3B Instruct 8bit | 125K / 4.1 GB | 528 | 7 |