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

BigQwen2.5 52B Instruct by mlabonne

 »  All LLMs  »  mlabonne  »  BigQwen2.5 52B Instruct   URL Share it on

  20   

BigQwen2.5 52B Instruct is an open-source language model by mlabonne. Features: 32b LLM, VRAM: 105GB, Context: 32K, License: apache-2.0, Instruction-Based, Merged, LLM Explorer Score: 0.28.

  Merged Model   Ara   Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-32b-in...   Conversational   Deu   Endpoints compatible   Eng   Fra   Instruct   Ita   Jpn   Kor   Model-index   Por   Qwen2   Region:us   Rus   Safetensors   Sharded   Spa   Tensorflow   Tha   Vie   Zho
Model Card on HF 🤗: https://huggingface.co/mlabonne/BigQwen2.5-52B-Instruct 

BigQwen2.5 52B Instruct Benchmarks

MMLU Pro: 50.22
GPQA: 6.94
MUSR: 10.45
BBH: 59.81
IFEval: 79.13 vs 88 (so35)-10.1%
MATH Lvl 5: 54.76
LLME Score: 0.28294
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
BigQwen2.5 52B Instruct (mlabonne/BigQwen2.5-52B-Instruct)
🌟 Advertise your project 🚀

BigQwen2.5 52B Instruct Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
creative writing
Additional Notes 
This is a self-merged model, use at your own risk.
Supported Languages 
en (proficient)
Training Details 
Methodology:
self-merge with MergeKit
Context Length:
131072
LLM NameBigQwen2.5 52B Instruct
Repository 🤗https://huggingface.co/mlabonne/BigQwen2.5-52B-Instruct 
Base Model(s)  Qwen/Qwen2.5-32B-Instruct   Qwen/Qwen2.5-32B-Instruct
Merged ModelYes
Model Size32b
Required VRAM105 GB
Updated2025-10-22
Maintainermlabonne
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-22   4.9 GB: 2-of-22   5.0 GB: 3-of-22   4.8 GB: 4-of-22   5.0 GB: 5-of-22   4.9 GB: 6-of-22   4.8 GB: 7-of-22   5.0 GB: 8-of-22   4.8 GB: 9-of-22   4.9 GB: 10-of-22   5.0 GB: 11-of-22   4.8 GB: 12-of-22   5.0 GB: 13-of-22   4.9 GB: 14-of-22   4.8 GB: 15-of-22   5.0 GB: 16-of-22   4.9 GB: 17-of-22   4.9 GB: 18-of-22   4.9 GB: 19-of-22   4.9 GB: 20-of-22   4.9 GB: 21-of-22   1.9 GB: 22-of-22
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to BigQwen2.5 52B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB122
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB3117
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB104
Franqwenstein 35B128K / 69.8 GB38
ELYZA Thinking 1.0 Qwen 32B128K / 65.8 GB12847
Hamanasu Magnum QwQ 32B128K / 65.8 GB2959
Archaeo 32B KTO128K / 65.8 GB44
Qwen2.5 32B Gokgok Step3128K / 65.7 GB60
Qwen2.5 32B Dark Days Stage2128K / 65.8 GB70
Qwen2.5 32B YOYO MIX128K / 65.7 GB52
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/BigQwen2.5-52B-Instruct.

Rank the BigQwen2.5 52B Instruct 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? 52605 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer