LLM Name | Qwen3 14B V0.2 Deepresearch No Think 100 Step |
Repository ๐ค | https://huggingface.co/jan-hq/Qwen3-14B-v0.2-deepresearch-no-think-100-step |
Model Size | 14b |
Required VRAM | 29.5 GB |
Updated | 2025-06-16 |
Maintainer | jan-hq |
Model Type | qwen3 |
Model Files | |
Model Architecture | Qwen3ForCausalLM |
Context Length | 40960 |
Model Max Length | 40960 |
Transformers Version | 4.52.3 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen3 14B | 40K / 29.7 GB | 829599 | 222 |
Qwen3 14B FP8 | 40K / 16.4 GB | 20845 | 27 |
Dhanishtha 2.0 Preview | 40K / 29.5 GB | 573 | 55 |
Qwen3 14B | 40K / 29.5 GB | 14252 | 10 |
Qwen3 14B Abliterated | 40K / 59 GB | 1655 | 38 |
GrayLine Qwen3 14B | 40K / 29.5 GB | 873 | 24 |
Merged16 Kto Qwen3 14B 2 | 40K / 29.5 GB | 46 | 0 |
...14B Instruct Wildfeedback Seed | 40K / 29.5 GB | 74 | 0 |
Smoothie Qwen3 14B | 40K / 29.5 GB | 1910 | 5 |
...Omega Directive Qwen3 14B V1.1 | 40K / 29.5 GB | 930 | 21 |
๐ 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! ๐