Model Card on HF 🤗: https://huggingface.co/AGI-0/Art-v0-3B
Art V0 3B Benchmarks
MMLU Pro: 1.98
GPQA: 1.23
MUSR: 5
BBH: 8.03
IFEval: 31.92 vs 88 (so35)-63.7%
MATH Lvl 5: 24.62
LLME Score: 0.2304
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)
Art V0 3B Parameters and Internals
| LLM Name | Art V0 3B |
| Repository 🤗 | https://huggingface.co/AGI-0/Art-v0-3B |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2025-08-27 |
| Maintainer | AGI-0 |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Art V0 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saba2 3B | 128K / 6.2 GB | 5 | 0 |
| UIGEN T1.5 3B | 117K / 6.2 GB | 33 | 1 |
| Tessa T1 3B | 117K / 6.2 GB | 7 | 5 |
| Qwen2.5 3B Instruct | 32K / 6.2 GB | 4746260 | 319 |
| SmallThinker 3B Preview | 32K / 6.8 GB | 31788 | 410 |
| Chirp 01 | 32K / 6.2 GB | 5 | 14 |
| Menda 3B 500 | 32K / 6.2 GB | 5 | 0 |
| Menda 3B 750 | 32K / 6.2 GB | 3 | 1 |
| Calme 3.2 Baguette 3B | 32K / 11 GB | 2098 | 1 |
| Qwen2.5 3B Model Stock V3.1 | 32K / 6.8 GB | 3 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than AGI-0/Art-v0-3B .
Rank the Art V0 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124