Qwen2.5 3B Benchmarks
MMLU Pro: 24.48
GPQA: 6.38
MUSR: 11.76
BBH: 24.3
IFEval: 26.9 vs 88 (so35)-69.4%
MATH Lvl 5: 7.93
LLME Score: 0.41587
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)
Qwen2.5 3B Parameters and Internals
| LLM Name | Qwen2.5 3B |
| Repository 🤗 | https://huggingface.co/Qwen/Qwen2.5-3B |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2024-10-04 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2.5 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 3B Instruct | 32K / 6.2 GB | 72666 | 45 |
| Qwen2.5 3B Instruct | 32K / 6.2 GB | 1274 | 1 |
| Replete LLM V2.5 Qwen 3B | 32K / 6.8 GB | 74 | 1 |
| Qwen 2.5 3B RP | 32K / 6.8 GB | 27 | 1 |
| Qwen 2.5 3B Evol CoT | 32K / 6.8 GB | 26 | 0 |
| Qwen 2.5 3B Evol CoT V2 | 32K / 6.8 GB | 26 | 0 |
| Qwen2.5 3B Instruct Bnb 4bit | 32K / 2 GB | 837 | 2 |
| Qwen2.5 3B Instruct AWQ | 32K / 2.7 GB | 697 | 2 |
| Qwen2.5 3B Instruct GPTQ Int8 | 32K / 3.5 GB | 226 | 2 |
| Polanka Qwen2 3B V0.1 | 128K / 6.9 GB | 21 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-3B .
Rank the Qwen2.5 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? 36542 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803