4-bit 4bit Autotrain compatible Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Bitsandbytes Conversational Deepseek En Endpoints compatible Quantized Qwen Qwen2 Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit
DeepSeek R1 Distill Qwen 32B Bnb 4bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
DeepSeek R1 Distill Qwen 32B Bnb 4bit Parameters and Internals
| LLM Name | DeepSeek R1 Distill Qwen 32B Bnb 4bit |
| Repository 🤗 | https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 19.2 GB |
| Updated | 2025-03-12 |
| Maintainer | unsloth |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives to DeepSeek R1 Distill Qwen 32B Bnb 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| QwQ 32B 4bit | 128K / 18.5 GB | 2865 | 23 |
| ...pSeek R1 Distill Qwen 32B 4bit | 128K / 18.5 GB | 400169 | 36 |
| QwQ 32B Unsloth Bnb 4bit | 128K / 22.5 GB | 5674 | 16 |
| QwQ 32B 8bit | 128K / 34.9 GB | 1423 | 10 |
| ...Q 32B Gptqmodel 4bit Vortex V1 | 128K / 21.3 GB | 905 | 5 |
| QwQ 32B Bnb 4bit | 128K / 19.2 GB | 1665 | 3 |
| Qwen QwQ 32B 425bpw H6 EXL2 | 128K / 18.8 GB | 313 | 4 |
| QwQ 32B 6bit | 128K / 26.7 GB | 326 | 3 |
| QwQ 32B 8.0bpw H8 EXL2 | 128K / 33.6 GB | 233 | 3 |
| ...till Qwen 32B Unsloth Bnb 4bit | 128K / 35.6 GB | 5240 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit .
Rank the DeepSeek R1 Distill Qwen 32B Bnb 4bit Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 44902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227