LLM Name | Qwen3 14B Base |
Repository ๐ค | https://huggingface.co/Qwen/Qwen3-14B-Base |
Model Size | 14b |
Required VRAM | 29.7 GB |
Updated | 2025-09-13 |
Maintainer | Qwen |
Model Type | qwen3 |
Model Files | |
Model Architecture | Qwen3ForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.51.0 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Errors | replace |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...wen3 14B Base Unsloth Bnb 4bit | 4 | 5921 | 10 GB |
Qwen3 14B MLX 4bit | 5 | 229 | 7 GB |
Qwen3 14B MLX 8bit | 3 | 133 | 15 GB |
Qwen3 14B MLX 6bit | 2 | 81 | 11 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
SimpleChat 14B V1 | 195K / 29.5 GB | 37 | 2 |
...0528DistillQwen 14B V27.3 200K | 195K / 29.5 GB | 18 | 4 |
...uct 21B Brainstorm20x 128K Ctx | 128K / 84.1 GB | 21 | 0 |
MiroThinker 14B DPO V0.2 | 64K / 29.7 GB | 32 | 4 |
Hermes 4 14B | 40K / 29.5 GB | 3376 | 80 |
Qwen3 14B | 40K / 29.7 GB | 1203827 | 265 |
Hermes 4 14B FP8 | 40K / 16.4 GB | 3510 | 8 |
Qwen3 14B FP8 | 40K / 16.4 GB | 75661 | 34 |
Qwen3 14B | 40K / 29.5 GB | 31565 | 10 |
Qwen3 14B Abliterated | 40K / 59 GB | 9607 | 39 |
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