LLM Name | Qwen3 30B A3B.w4a16 |
Repository ๐ค | https://huggingface.co/nytopop/Qwen3-30B-A3B.w4a16 |
Base Model(s) | |
Model Size | 30b |
Required VRAM | 16.7 GB |
Updated | 2025-06-01 |
Maintainer | nytopop |
Model Type | qwen3_moe |
Model Files | |
Model Architecture | Qwen3MoeForCausalLM |
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 |
---|---|---|---|
...0B A6B 16 Extreme 128K Context | 128K / 61.1 GB | 89 | 7 |
Qwen3 30B A3B | 40K / 61.1 GB | 299905 | 612 |
Qwen3 30B A3B FP8 | 40K / 32.5 GB | 196539 | 62 |
Qwen3 16B A3B | 40K / 32.1 GB | 1765 | 80 |
Qwen3 30B A6B 16 Extreme | 40K / 61.1 GB | 1309 | 49 |
Qwen3 30B A3B Abliterated | 40K / 61.1 GB | 1580 | 31 |
...en3 30B A3B Abliterated Erotic | 40K / 61.1 GB | 349 | 11 |
Qwen3 30B A3B Bf16 | 40K / 61.2 GB | 743 | 2 |
Qwen3 30B A1.5B High Speed | 40K / 61.1 GB | 315 | 8 |
... 30B A7.5B 24 Grand Brainstorm | 40K / 61.1 GB | 72 | 9 |
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