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 14B by Qwen

 »  All LLMs  »  Qwen  »  Qwen2.5 Coder 14B   URL Share it on

  10962   
  Arxiv:2309.00071   Arxiv:2407.10671   Arxiv:2409.12186   Autotrain compatible Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2.5-14b   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-14B 

Qwen2.5 Coder 14B Benchmarks

MMLU Pro: 39.13
GPQA: 5.7
MUSR: 6.39
BBH: 40.52
IFEval: 34.73 vs 88 (so35)-60.5%
MATH Lvl 5: 22.51
LLME Score: 0.36556
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 14B (Qwen/Qwen2.5-Coder-14B)

Qwen2.5 Coder 14B 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 14B
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-Coder-14B 
Base Model(s)  Qwen/Qwen2.5-14B   Qwen/Qwen2.5-14B
Model Size14b
Required VRAM29.7 GB
Updated2025-03-14
MaintainerQwen
Model Typeqwen2
Model Files  5.0 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.7 GB: 6-of-6
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 14B

Model
Likes
Downloads
VRAM
Qwen2.5 Coder 14B Bnb 4bit314709 GB

Best Alternatives to Qwen2.5 Coder 14B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B YOYO V4986K / 29.7 GB3573
ZYH LLM Qwen2.5 14B V2986K / 29.7 GB1181
Mergekit Model Stock Ggfjmyf986K / 29.7 GB140
Mergekit Model Stock Injkqri986K / 29.7 GB331
Primal Opus 14B Optimus V2128K / 29.7 GB37213
Qwen2.5 14B ReasoningMerge128K / 29.7 GB3073
Qwen2.5 14B YOYO Latest128K / 29.7 GB670
DeepSeek R1 Qwen Coder 8B128K / 16.6 GB7010
...1 DeepSeekR1 Coder 14B Preview128K / 29.7 GB1982
Qwen2.5 14B Coder Merge128K / 29.7 GB1192
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-Coder-14B.

Rank the Qwen2.5 Coder 14B 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? 45019 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