LLM Name | Qwen3 32B MLX 4bit |
Repository ๐ค | https://huggingface.co/Qwen/Qwen3-32B-MLX-4bit |
Model Size | 32b |
Required VRAM | 17.4 GB |
Updated | 2025-06-17 |
Maintainer | Qwen |
Model Type | qwen3 |
Model Files | |
Quantization Type | 4bit |
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 | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen3 32B Unsloth Bnb 4bit | 40K / 39.6 GB | 14021 | 8 |
Qwen3 32B 4bit | 40K / 18.5 GB | 1684 | 1 |
Qwen3 32B 8bit | 40K / 34.9 GB | 1375 | 0 |
Qwen3 32B 128K GGUF | 128K / 7.8 GB | 11728 | 21 |
Qwen3 32B | 40K / 65.6 GB | 752768 | 392 |
Qwen3 32B AWQ | 40K / 19.4 GB | 107411 | 68 |
Qwen3 32B GGUF | 40K / 7.8 GB | 41860 | 69 |
Qwen3 32B FP8 | 40K / 34.5 GB | 43008 | 51 |
...Distill Qwen3 32B Preview0 QAT | 40K / 65.8 GB | 246 | 26 |
Qwen3 72B Embiggened | 40K / 146 GB | 127 | 17 |
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