WeVisDoc 4B is an open-source language model by tencent. Features: 4b LLM, VRAM: 9.7GB, License: apache-2.0, LLM Explorer Score: 0.3.
| LLM Name | WeVisDoc 4B |
| Repository 🤗 | https://huggingface.co/tencent/WeVisDoc-4B |
| Model Size | 4b |
| Required VRAM | 9.7 GB |
| Updated | 2026-09-20 |
| Maintainer | tencent |
| Model Type | qwen3_vl |
| Model Files | |
| Supported Languages | en zh |
| Model Architecture | Qwen3VLForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Transformers Version | 4.57.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| WeVisOne VL 4B | 0K / 19.3 GB | 2605 | 58 |
| Qwen3 VL 4B Instruct | 0K / 8.9 GB | 3611570 | 437 |
| MinerU Popo | 0K / 17.6 GB | 26895 | 4 |
| Qwen3 VL 4B Instruct FP8 | 0K / 6.1 GB | 301103 | 65 |
| Qwen3 VL 4B Thinking Pashto Zi | 0K / 8.9 GB | 1426 | 0 |
| VIG Qwen3 VL Thinking 4B | 0K / 9.7 GB | 48 | 1 |
| AA VL 4B | 0K / 8.9 GB | 87 | 0 |
| Qwen3 VL 4B VQA SFT | 0K / 8.9 GB | 40 | 0 |
| Qwen3 VL 4B Thinking | 0K / 8.9 GB | 21715 | 118 |
| UI UG2 4B | 0K / 8.9 GB | 7 | 1 |