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

Qwen2.5 Coder 32B by Qwen

 »  All LLMs  »  Qwen  »  Qwen2.5 Coder 32B   URL Share it on

  7132   

Qwen2.5 Coder 32B is an open-source language model by Qwen. Features: 32b LLM, VRAM: 65.8GB, Context: 32K, License: apache-2.0, Code Generating, LLM Explorer Score: 0.33, HumanEval: 57.1.

  Arxiv:2309.00071   Arxiv:2407.10671   Arxiv:2409.12186   Autotrain compatible Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2.5-32b   Code   Codegen   Codeqwen   Conversational   En   Endpoints compatible   Qwen   Qwen-coder   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-Coder-32B 

Qwen2.5 Coder 32B Benchmarks

MMLU Pro: 47.81
GPQA: 12.86
MUSR: 15.87
BBH: 48.51
IFEval: 43.63 vs 88 (so35)-50.4%
HumanEvalA: 55.07
Python Eva: 57.1 vs 92 (so35)-37.9%
Java Eval: 65.49
Javascript: 65.07
CPP Eval: 64.35
PHP Eval: 62.7
Julia Eval: 51.28
D Eval: 32.3
Lua Eval: 57.25
R Eval: 31.2
Racket Eva: 47.93
Rust Eval: 65.94
Swift Eval: 60.21
MATH Lvl 5: 30.89
LLME Score: 0.32862
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 Coder 32B (Qwen/Qwen2.5-Coder-32B)
🌟 Advertise your project 🚀

Qwen2.5 Coder 32B Parameters and Internals

Model Type 
text-generation
Use Cases 
Applications:
code generation, code reasoning, code fixing
Limitations:
not recommended for conversational tasks
Additional Notes 
The model has long-context support allowing up to 128K tokens processed.
Supported Languages 
en (high)
Training Details 
Data Sources:
source code, text-code grounding, Synthetic data
Data Volume:
5.5 trillion tokens
Methodology:
transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Context Length:
131072
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Input Output 
Accepted Modalities:
text
Performance Tips:
Apply post-training for conversational tasks; adjust `rope_scaling` for long contexts.
Release Notes 
Version:
2.5
Date:
2024
Notes:
Significant improvements in code capabilities and long-context support.
LLM NameQwen2.5 Coder 32B
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-Coder-32B 
Base Model(s)  Qwen/Qwen2.5-32B   Qwen/Qwen2.5-32B
Model Size32b
Required VRAM65.8 GB
Updated2025-10-19
MaintainerQwen
Model Typeqwen2
Model Files  4.9 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   2.1 GB: 14-of-14
Supported Languagesen
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2.5 Coder 32B

Model
Likes
Downloads
VRAM
Qwen2.5 Coder 32B Bnb 4bit585319 GB
...truct Gptqmodel 4bit Vortex V1161021 GB
Qwen2.5 Coder 32B 8bit42234 GB
Qwen2.5 Coder 32B 4bit32418 GB

Best Alternatives to Qwen2.5 Coder 32B

Best Alternatives
Context / RAM
Downloads
Likes
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB122
...2.5 Godzilla Coder V2 51B 128K128K / 102.1 GB81
Qwen2.5 32B YOYO V2128K / 65.7 GB101
QwQ Coder R1 Distill 32B128K / 65.8 GB60
Qwen2.5 32B YOYO MIX128K / 65.7 GB52
QwQ Coder 32B128K / 65.7 GB168
Qwen2.5 Coder 32B YOYO128K / 65.8 GB62
YOYO O1 32B V2128K / 65.7 GB23
QwQ Qwen2.5 Coder Instruct 32B128K / 65.8 GB430
...ill Qwen Coder 32B Fusion 9010128K / 65.8 GB827

Rank the Qwen2.5 Coder 32B 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? 51638 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 v20241124
  Support LLM Explorer