LLM Name | DeepSeek R1 Distill Qwen 32B Japanese 4bit |
Repository 🤗 | https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-32B-Japanese-4bit |
Base Model(s) | |
Model Size | 32b |
Required VRAM | 18.5 GB |
Updated | 2025-06-11 |
Maintainer | mlx-community |
Model Type | qwen2 |
Model Files | |
Supported Languages | ja |
Quantization Type | 4bit |
Model Architecture | Qwen2ForCausalLM |
License | mit |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.47.0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|end▁of▁sentence|> |
Vocabulary Size | 152064 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
QwQ 32B Unsloth Bnb 4bit | 128K / 22.5 GB | 4446 | 45 |
QwQ 32B 4bit | 128K / 18.5 GB | 1356 | 36 |
...k R1 Distill Qwen 32B Bnb 4bit | 128K / 19.2 GB | 4723 | 24 |
...pSeek R1 Distill Qwen 32B 4bit | 128K / 18.5 GB | 3141 | 41 |
...Q 32B Gptqmodel 4bit Vortex V1 | 128K / 21.3 GB | 1052 | 11 |
QwQ 32B 8bit | 128K / 34.9 GB | 955 | 13 |
QwQ 32B Bnb 4bit | 128K / 19.2 GB | 1165 | 3 |
QwQ 32B Bnb 4bit | 128K / 19.2 GB | 850 | 2 |
...till Qwen 32B Unsloth Bnb 4bit | 128K / 35.6 GB | 1321 | 10 |
...ogito V1 Preview Qwen 32B 4bit | 128K / 18.5 GB | 74 | 5 |
🆘 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! 🌟