LLM Name | Qwen3 14B AWQ |
Repository ๐ค | https://huggingface.co/Qwen/Qwen3-14B-AWQ |
Base Model(s) | |
Model Size | 14b |
Required VRAM | 10 GB |
Updated | 2025-08-21 |
Maintainer | Qwen |
Model Type | qwen3 |
Model Files | |
AWQ Quantization | Yes |
Quantization Type | awq |
Model Architecture | Qwen3ForCausalLM |
License | apache-2.0 |
Context Length | 40960 |
Model Max Length | 40960 |
Transformers Version | 4.51.3 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | float16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen3 14B 4bit AWQ | 40K / 8.3 GB | 904 | 3 |
Qwen3 14B Unsloth Bnb 4bit | 40K / 11.2 GB | 72560 | 8 |
Qwen3 14B MLX 4bit | 40K / 8.3 GB | 48982 | 4 |
Merged16 Sft Qwen3 32 2 | 40K / 29.5 GB | 294 | 0 |
Bee1reason Arabic Qwen 14B | 40K / 29.5 GB | 1094 | 15 |
Bee1reason Arabic Qwen 14B | 40K / 29.5 GB | 584 | 8 |
Merged16 Kto Qwen3 14B | 40K / 29.5 GB | 40 | 0 |
Qwen3 14B MLX 4bit | 40K / 7.9 GB | 199 | 5 |
Qwen3 14B 4bit DWQ 053125 | 40K / 8.3 GB | 119 | 3 |
Qwen3 Codellm | 40K / 29.5 GB | 23 | 0 |
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