LLM Name | Qwen3 30B A3B MLX 4bit |
Repository ๐ค | https://huggingface.co/lmstudio-community/Qwen3-30B-A3B-MLX-4bit |
Base Model(s) | |
Model Size | 30b |
Required VRAM | 17.2 GB |
Updated | 2025-06-09 |
Maintainer | lmstudio-community |
Model Type | qwen3_moe |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Qwen3MoeForCausalLM |
License | apache-2.0 |
Context Length | 40960 |
Model Max Length | 40960 |
Transformers Version | 4.51.0 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen3 30B A3B 4bit DWQ 053125 | 40K / 17.2 GB | 629 | 3 |
Qwen3 30B A3B 4bit DWQ | 40K / 17.2 GB | 1495 | 25 |
Qwen3 30B A3B 4bit DWQ 0508 | 40K / 17.2 GB | 1098 | 13 |
Qwen3 30B A3B 4bit | 40K / 17.2 GB | 1590 | 10 |
Qwen3 30B A3B 8bit | 40K / 32.5 GB | 1362 | 6 |
...wen3 30B A3B 4bit DWQ 05082025 | 40K / 17.2 GB | 760 | 5 |
Qwen3 30B A3B 6bit | 40K / 24.7 GB | 888 | 2 |
Q3 30B A3B Designant | 32K / 61.1 GB | 182 | 13 |
Qwen3 30B A3B Base Bnb 4bit | 32K / 16.7 GB | 1352 | 0 |
Q3 30B Ft Ep2 Merged | 32K / 61.1 GB | 80 | 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