LLM Name | Qwen3 4B MLX 4bit |
Repository ๐ค | https://huggingface.co/Qwen/Qwen3-4B-MLX-4bit |
Model Size | 4b |
Required VRAM | 2.1 GB |
Updated | 2025-07-10 |
Maintainer | Qwen |
Model Type | qwen3 |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Qwen3ForCausalLM |
License | apache-2.0 |
Context Length | 65536 |
Model Max Length | 65536 |
Transformers Version | 4.51.3 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen3 4B Unsloth Bnb 4bit | 40K / 3.6 GB | 56710 | 7 |
Qwen3 4B 4bit | 40K / 2.3 GB | 7247 | 7 |
Qwen3 4B 4bit DWQ 053125 | 40K / 2.3 GB | 2742 | 2 |
Qwen3 4B 4bit DWQ | 40K / 2.3 GB | 1865 | 3 |
...d Qwen3 4B Abliterated V1 4bit | 40K / 2.3 GB | 1889 | 2 |
Qwen3 4B MLX 8bit | 40K / 4.2 GB | 294 | 2 |
...d Qwen3 4B Abliterated V1 6bit | 40K / 3.3 GB | 77 | 2 |
Qwen3 4B 3kingdoms Augmented | 40K / 8.1 GB | 5 | 0 |
Qwen3 4B Base Unsloth Bnb 4bit | 32K / 3.3 GB | 17684 | 0 |
Zeta Qwen3 4B Sft | 32K / 8.1 GB | 28 | 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