DeepSeek R1 Distill Qwen 32B Unsloth Bnb 4bit by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  DeepSeek R1 Distill Qwen 32B Unsloth Bnb 4bit   URL Share it on

  Arxiv:2501.12948   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

DeepSeek R1 Distill Qwen 32B Unsloth 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").
DeepSeek R1 Distill Qwen 32B Unsloth Bnb 4bit (unsloth/DeepSeek-R1-Distill-Qwen-32B-unsloth-bnb-4bit)

DeepSeek R1 Distill Qwen 32B Unsloth Bnb 4bit Parameters and Internals

LLM NameDeepSeek R1 Distill Qwen 32B Unsloth Bnb 4bit
Repository ๐Ÿค—https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-unsloth-bnb-4bit 
Base Model(s)  DeepSeek R1 Distill Qwen 32B   deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Model Size32b
Required VRAM35.6 GB
Updated2025-03-24
Maintainerunsloth
Model Typeqwen2
Model Files  4.9 GB: 1-of-8   5.0 GB: 2-of-8   5.0 GB: 3-of-8   4.8 GB: 4-of-8   5.0 GB: 5-of-8   4.7 GB: 6-of-8   4.6 GB: 7-of-8   1.6 GB: 8-of-8
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.49.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|vision_pad|>
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to DeepSeek R1 Distill Qwen 32B Unsloth Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
QwQ 32B Unsloth Bnb 4bit128K / 22.5 GB1862333
...pSeek R1 Distill Qwen 32B 4bit128K / 18.5 GB16490539
QwQ 32B 4bit128K / 18.5 GB538533
...k R1 Distill Qwen 32B Bnb 4bit128K / 19.2 GB5570823
QwQ 32B 8bit128K / 34.9 GB269511
...Q 32B Gptqmodel 4bit Vortex V1128K / 21.3 GB18397
QwQ 32B Bnb 4bit128K / 19.2 GB34333
...T1 Flash Lightest 32B Mlx 4Bit128K / 18.5 GB9915
QwQ 32B 6bit128K / 26.7 GB7613
Qwen QwQ 32B 425bpw H6 EXL2128K / 18.8 GB3684
Note: green Score (e.g. "73.2") means that the model is better than unsloth/DeepSeek-R1-Distill-Qwen-32B-unsloth-bnb-4bit.

Rank the DeepSeek R1 Distill Qwen 32B Unsloth Bnb 4bit Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 45546 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227