Arxiv:2309.00071 Arxiv:2504.16891 Autotrain compatible Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b Code Conversational Dataset:mlabonne/finetome-100k Dataset:unsloth/openmathreason... En Endpoints compatible Math Moe Qwen3 Region:us Safetensors Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/prithivMLmods/Draconis-Qwen3_Math-4B-Preview
Draconis Qwen3 Math 4B Preview 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)
Draconis Qwen3 Math 4B Preview Parameters and Internals
| LLM Name | Draconis Qwen3 Math 4B Preview |
| Repository 🤗 | https://huggingface.co/prithivMLmods/Draconis-Qwen3_Math-4B-Preview |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 8.1 GB |
| Updated | 2025-06-01 |
| Maintainer | prithivMLmods |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Draconis Qwen3 Math 4B Preview
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 4B FP8 | 40K / 5.2 GB | 26526 | 22 |
| Qwen3 4B | 40K / 8.1 GB | 18149 | 5 |
| Qwen3 4B Esper3 | 40K / 16.1 GB | 5272 | 7 |
| Qwen3 4B Abliterated | 40K / 8.1 GB | 475 | 12 |
| ...iefied Qwen3 4B Abliterated V1 | 40K / 8.1 GB | 535 | 10 |
| Bootes Qwen3 Coder Reasoning | 40K / 8.1 GB | 284 | 2 |
| ...iefied Qwen3 4B Abliterated V2 | 40K / 8.1 GB | 71 | 4 |
| Jade Qwen3 4b | 40K / 8.1 GB | 48 | 0 |
| BetaCeti Beta 4B Prime1 | 40K / 8.1 GB | 14 | 2 |
| Crux Qwen3 OpenThinking 4B | 40K / 8.1 GB | 26 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than prithivMLmods/Draconis-Qwen3_Math-4B-Preview .
Rank the Draconis Qwen3 Math 4B Preview 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? 47753 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227