Base model:finetune:qingy2024/... Base model:qingy2024/qwark-4b Dataset:qingy2024/qwark-corpus Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/qingy2024/Qwarkstar-4B
Qwarkstar 4B Benchmarks
MMLU Pro: 15.84
GPQA: 9.96
MUSR: 14.09
BBH: 16.57
IFEval: 19.94 vs 88 (so35)-77.3%
MATH Lvl 5: 8.61
LLME Score: 0.24923
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)
Qwarkstar 4B Parameters and Internals
| LLM Name | Qwarkstar 4B |
| Repository 🤗 | https://huggingface.co/qingy2024/Qwarkstar-4B |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 9 GB |
| Updated | 2025-07-25 |
| Maintainer | qingy2024 |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwarkstar 4B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen1.5 4B Chat | 32K / 7.9 GB | 234587 | 41 |
| Qwarkstar 4B Instruct Preview | 32K / 9 GB | 11 | 2 |
| Qwen1.5 4B | 32K / 7.9 GB | 15986 | 35 |
| Qwarkstar 4B Instruct | 32K / 9 GB | 30 | 1 |
| Sailor 4B | 32K / 7.9 GB | 8 | 6 |
| Nusantara 4B Indo Chat | 32K / 7.9 GB | 8 | 1 |
| Sailor 4B Chat | 32K / 7.9 GB | 7 | 2 |
| Reyna CoT 4B V0.1 | 32K / 7.9 GB | 5 | 6 |
| Bahasa 4B Chat | 32K / 7.9 GB | 903 | 6 |
| Blossom V5 4B | 32K / 7.9 GB | 8 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than qingy2024/Qwarkstar-4B .
Rank the Qwarkstar 4B 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? 50068 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124