LLM Name | DeepSeek R1 0528 Qwen3 8B 4bit DWQ |
Repository 🤗 | https://huggingface.co/mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit-DWQ |
Base Model(s) | |
Model Size | 8b |
Required VRAM | 4.6 GB |
Updated | 2025-07-30 |
Maintainer | mlx-community |
Model Type | qwen3 |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Qwen3ForCausalLM |
License | mit |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.51.0 |
Tokenizer Class | LlamaTokenizerFast |
Padding Token | <|end▁of▁sentence|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...0528 Qwen3 8B Unsloth Bnb 4bit | 128K / 7.5 GB | 25368 | 11 |
...Seek R1 0528 Qwen3 8B Bnb 4bit | 128K / 6.1 GB | 27961 | 7 |
DeepSeek R1 0528 Qwen3 8B 4bit | 128K / 4.6 GB | 1208 | 4 |
Qwen3 8B LQA 14e Full | 128K / 16.4 GB | 91 | 0 |
...0528 Qwen3 8B Unsloth Bnb 4bit | 128K / 16.4 GB | 6 | 0 |
Qwen3 8B Unsloth Bnb 4bit | 40K / 7.5 GB | 76142 | 8 |
Qwen3 8B Bnb 4bit | 40K / 6.1 GB | 5557 | 1 |
Qwen3 8B 4bit | 40K / 4.6 GB | 2266 | 5 |
...d Qwen3 8B Abliterated V1 4bit | 40K / 4.6 GB | 966 | 2 |
Qwen3 8B 4bit DWQ | 40K / 4.6 GB | 916 | 2 |
🆘 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! 🌟