LLM Name | Deepseek R1 Distill Qwen 1.5B |
Repository 🤗 | https://huggingface.co/mlx-community/deepseek-r1-distill-qwen-1.5b |
Base Model(s) | |
Model Size | 1.5b |
Required VRAM | 3.5 GB |
Updated | 2025-07-02 |
Maintainer | mlx-community |
Model Type | qwen2 |
Model Files | |
Model Architecture | Qwen2ForCausalLM |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.44.0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|end▁of▁sentence|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
ReaderLM V2 | 500K / 3.1 GB | 12080 | 661 |
Reader Lm 1.5B | 250K / 3.1 GB | 2181 | 598 |
DeepSeek R1 Distill Qwen 1.5B | 128K / 3.5 GB | 1174511 | 1249 |
...n Research Reasoning Qwen 1.5B | 128K / 3.5 GB | 13282 | 170 |
DeepScaleR 1.5B Preview | 128K / 7.1 GB | 147579 | 561 |
Qwen2.5 1.5B | 128K / 3.1 GB | 478425 | 106 |
AceInstruct 1.5B | 128K / 3.5 GB | 5382 | 20 |
DeepCoder 1.5B Preview | 128K / 7.1 GB | 5092 | 66 |
AlphaMaze V0.2 1.5B | 128K / 3.5 GB | 9887 | 93 |
Qwen2 1.5B | 128K / 3.1 GB | 86843 | 94 |
🆘 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! 🌟