Model Card on HF 🤗: https://huggingface.co/SvalTek/Qwen3-14B-DarkFusion
Qwen3 14B DarkFusion 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)
Qwen3 14B DarkFusion Parameters and Internals
| LLM Name | Qwen3 14B DarkFusion |
| Repository 🤗 | https://huggingface.co/SvalTek/Qwen3-14B-DarkFusion |
| Merged Model | Yes |
| Model Size | 14b |
| Required VRAM | 29.5 GB |
| Updated | 2025-08-26 |
| Maintainer | SvalTek |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.55.4 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151669 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen3 14B DarkFusion
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SimpleChat 14B V1 | 195K / 29.5 GB | 30 | 2 |
| ...0528DistillQwen 14B V27.3 200K | 195K / 29.5 GB | 15 | 4 |
| ...uct 21B Brainstorm20x 128K Ctx | 128K / 84.1 GB | 29 | 0 |
| Qwen3 14B | 40K / 29.7 GB | 956363 | 251 |
| Qwen3 14B FP8 | 40K / 16.4 GB | 68456 | 31 |
| Qwen3 14B | 40K / 29.5 GB | 22431 | 9 |
| QiMing Pantheon Qwen3 14B | 40K / 29.2 GB | 55 | 1 |
| MiroThinker 14B DPO V0.1 | 40K / 29.7 GB | 100 | 13 |
| Dhanishtha 2.0 Preview | 40K / 29.5 GB | 326 | 60 |
| MiroThinker 14B SFT V0.1 | 40K / 29.7 GB | 43 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than SvalTek/Qwen3-14B-DarkFusion .
Rank the Qwen3 14B DarkFusion 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? 50900 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124