LLM Name | Qwen3 30B A3B GPTQ |
Repository ๐ค | https://huggingface.co/AlphaGaO/Qwen3-30B-A3B-GPTQ |
Base Model(s) | |
Model Size | 30b |
Required VRAM | 16.9 GB |
Updated | 2025-05-12 |
Maintainer | AlphaGaO |
Model Type | qwen3_moe |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq |
Model Architecture | Qwen3MoeForCausalLM |
License | apache-2.0 |
Context Length | 40960 |
Model Max Length | 40960 |
Transformers Version | 4.51.3 |
Tokenizer Class | Qwen2TokenizerFast |
Padding Token | <unk> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen3 30B A3B MLX 4bit | 40K / 17.2 GB | 3708 | 17 |
Qwen3 30B A3B 4bit DWQ | 40K / 17.2 GB | 298 | 18 |
Qwen3 30B A3B 4bit DWQ 0508 | 40K / 17.2 GB | 167 | 9 |
Qwen3 30B A3B 4bit | 40K / 17.2 GB | 2111 | 6 |
Qwen3 30B A3B 8bit | 40K / 32.5 GB | 2014 | 5 |
...wen3 30B A3B 4bit DWQ 05082025 | 40K / 17.2 GB | 93 | 3 |
Qwen3 30B A3B 6bit | 40K / 24.7 GB | 569 | 2 |
Qwen3 30B A3B 128K GGUF | 128K / 9 GB | 39918 | 34 |
...0B A6B 16 Extreme 128K Context | 128K / 61.1 GB | 15 | 4 |
Qwen3 30B A3B | 40K / 61.1 GB | 155271 | 517 |
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