Model Card on HF 🤗: https://huggingface.co/Alibaba-NLP/WebSailor-3B
WebSailor 3B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
WebSailor 3B Parameters and Internals
| LLM Name | WebSailor 3B |
| Repository 🤗 | https://huggingface.co/Alibaba-NLP/WebSailor-3B |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2025-07-23 |
| Maintainer | Alibaba-NLP |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to WebSailor 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saba1.5 Pro 3B | 128K / 5.8 GB | 8 | 1 |
| ...b Sft Stage1.2 Ss1 Expert Math | 128K / 15.1 GB | 5 | 0 |
| ...2 Ss1 Expert Fictional Lyrical | 128K / 15.1 GB | 7 | 0 |
| ... Formattedtext Math Wiki Merge | 128K / 15.1 GB | 5 | 0 |
| ...tage1.1 Ss1 With Math.no Issue | 128K / 15.1 GB | 5 | 0 |
| ...ware Howto Formattedtext Merge | 128K / 15.1 GB | 6 | 0 |
| ...t Stage1.2 Ss1 Expert Software | 128K / 15.1 GB | 21 | 0 |
| ...1 No Redteam Skg Poem.no Issue | 128K / 15.1 GB | 6 | 0 |
| ...b Sft Stage1.2 Ss1 Expert News | 128K / 15.1 GB | 7 | 0 |
| ...ide 3b Orpo Stage1.1 Ss1 Orpo3 | 128K / 15.1 GB | 14 | 0 |
Rank the WebSailor 3B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 49991 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124