LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

DeepSeek R1 Distill Qwen 32B Abliterated 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  DeepSeek R1 Distill Qwen 32B Abliterated 4bit   URL Share it on

  19   
  4-bit   4bit   Abliterated   Autotrain compatible Base model:huihui-ai/deepseek-... Base model:quantized:huihui-ai...   Conversational   Endpoints compatible   Mlx   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Uncensored
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-32B-abliterated-4bit 

DeepSeek R1 Distill Qwen 32B Abliterated 4bit Benchmarks

LLME Score: 0.29679
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 Abliterated 4bit (mlx-community/DeepSeek-R1-Distill-Qwen-32B-abliterated-4bit)

DeepSeek R1 Distill Qwen 32B Abliterated 4bit Parameters and Internals

LLM NameDeepSeek R1 Distill Qwen 32B Abliterated 4bit
Repository 🤗https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-32B-abliterated-4bit 
Base Model(s)  ...1 Distill Qwen 32B Abliterated   huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated
Model Size32b
Required VRAM18.5 GB
Updated2025-02-22
Maintainermlx-community
Model Typeqwen2
Model Files  5.4 GB: 1-of-4   5.3 GB: 2-of-4   5.4 GB: 3-of-4   2.4 GB: 4-of-4
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Tokenizer ClassLlamaTokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to DeepSeek R1 Distill Qwen 32B Abliterated 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...pSeek R1 Distill Qwen 32B 4bit128K / 18.5 GB47987233
...k R1 Distill Qwen 32B Bnb 4bit128K / 19.2 GB5222221
...till Qwen 32B Unsloth Bnb 4bit128K / 35.6 GB33639
Qwen2.5 32B Bnb 4bit128K / 19.2 GB226983
PathFinderAI S1128K / 65.8 GB610
Deepseek R1 Qwen32b Mlx 6bit128K / 25.5 GB19314
...Distill Qwen 32B Japanese 4bit128K / 18.5 GB3092
...Distill Qwen 32B Japanese 8bit128K / 34.9 GB1392
EVA Instruct 32B EXL2 4.0128K / 17.7 GB103
PathfinderAI32K / 65.8 GB370
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/DeepSeek-R1-Distill-Qwen-32B-abliterated-4bit.

Rank the DeepSeek R1 Distill Qwen 32B Abliterated 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! 🌟

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? 43470 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer