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 25.5B Brainstorm by DavidAU

 »  All LLMs  »  DavidAU  »  DeepSeek R1 Distill Qwen 25.5B Brainstorm   URL Share it on

  30   
  128k context   Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Cognitivecomputations   Conversational   Cot   Deepseek   Endpoints compatible   Fine tune   Qwen 2.5   Qwen2   R1   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Thinking
Model Card on HF 🤗: https://huggingface.co/DavidAU/DeepSeek-R1-Distill-Qwen-25.5B-Brainstorm 

DeepSeek R1 Distill Qwen 25.5B Brainstorm Benchmarks

MMLU Pro: 40.26
GPQA: 18.12
MUSR: 25.24
BBH: 38.55
IFEval: 34.16 vs 88 (so35)-61.2%
MATH Lvl 5: 55.36
LLME Score: 0.33084
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 25.5B Brainstorm (DavidAU/DeepSeek-R1-Distill-Qwen-25.5B-Brainstorm)
🌟 Advertise your project 🚀

DeepSeek R1 Distill Qwen 25.5B Brainstorm Parameters and Internals

LLM NameDeepSeek R1 Distill Qwen 25.5B Brainstorm
Repository 🤗https://huggingface.co/DavidAU/DeepSeek-R1-Distill-Qwen-25.5B-Brainstorm 
Base Model(s)  DeepSeek R1 Distill Qwen 14B   deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Model Size14b
Required VRAM47.6 GB
Updated2025-06-17
MaintainerDavidAU
Model Typeqwen2
Model Files  1.6 GB: 1-of-52   1.6 GB: 2-of-52   1.0 GB: 3-of-52   0.9 GB: 4-of-52   1.0 GB: 5-of-52   1.0 GB: 6-of-52   1.0 GB: 7-of-52   0.9 GB: 8-of-52   1.0 GB: 9-of-52   1.0 GB: 10-of-52   1.0 GB: 11-of-52   0.9 GB: 12-of-52   1.0 GB: 13-of-52   1.0 GB: 14-of-52   1.0 GB: 15-of-52   0.9 GB: 16-of-52   1.0 GB: 17-of-52   1.0 GB: 18-of-52   1.0 GB: 19-of-52   0.9 GB: 20-of-52   1.0 GB: 21-of-52   1.0 GB: 22-of-52   1.0 GB: 23-of-52   0.9 GB: 24-of-52   1.0 GB: 25-of-52   1.0 GB: 26-of-52   1.0 GB: 27-of-52   1.0 GB: 28-of-52   1.0 GB: 29-of-52   1.0 GB: 30-of-52   1.0 GB: 31-of-52   1.0 GB: 32-of-52   1.0 GB: 33-of-52   1.0 GB: 34-of-52   1.0 GB: 35-of-52   1.0 GB: 36-of-52   1.0 GB: 37-of-52   1.0 GB: 38-of-52   1.0 GB: 39-of-52   1.0 GB: 40-of-52   1.0 GB: 41-of-52   1.0 GB: 42-of-52   1.0 GB: 43-of-52   1.0 GB: 44-of-52   1.0 GB: 45-of-52   1.0 GB: 46-of-52   1.0 GB: 47-of-52
Model ArchitectureQwen2ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.46.2
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to DeepSeek R1 Distill Qwen 25.5B Brainstorm

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB35677309
T3Q Qwen2.5 14B V1.0 E3986K / 29.7 GB85228
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB12357
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2544
Qwen2.5 14B YOYO Latest V2986K / 29.7 GB1290
Qwen2.5 14B YOYO V4986K / 29.7 GB314
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB488
Impish QWEN 14B 1M986K / 29.7 GB6017
...14B Instruct 1M GRPO Reasoning986K / 29.7 GB344
Etr1o V1.2986K / 29.7 GB130
Note: green Score (e.g. "73.2") means that the model is better than DavidAU/DeepSeek-R1-Distill-Qwen-25.5B-Brainstorm.

Rank the DeepSeek R1 Distill Qwen 25.5B Brainstorm 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? 48225 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 v20241124
  Support LLM Explorer