Qwen3 4B Code Reasoning by ertghiu256

 ยป  All LLMs  ยป  ertghiu256  ยป  Qwen3 4B Code Reasoning   URL Share it on

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-4b   Code   Coding   Conversational   Cot Dataset:nvidia/opencodereasoni... Dataset:vicgalle/creative-rubr...   Pytorch   Qwen3   Reasoning   Region:us   Sft   Sharded   Think   Thinking   Trl   Unsloth

Qwen3 4B Code Reasoning Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 4B Code Reasoning (ertghiu256/qwen3-4b-code-reasoning)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 4B Code Reasoning Parameters and Internals

LLM NameQwen3 4B Code Reasoning
Repository ๐Ÿค—https://huggingface.co/ertghiu256/qwen3-4b-code-reasoning 
Base Model(s)  Qwen3 4B   Qwen/Qwen3-4B   unsloth/Qwen3-4B   Qwen/Qwen3-4B
Model Size4b
Required VRAM8.1 GB
Updated2025-07-02
Maintainerertghiu256
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3 4B Code Reasoning

Best Alternatives
Context / RAM
Downloads
Likes
Jan Nano 128K128K / 8.1 GB2681175
Polaris 4B Preview128K / 8.1 GB1785105
Jan Nano 128K128K / 8.1 GB1342
Jan Nano40K / 8.1 GB34247432
Qwen3 Embedding 4B40K / 8.1 GB7795785
Qwen3 Reranker 4B40K / 8.1 GB3520771
QVikhr 3 4B Instruction40K / 8.1 GB1489
Qwen3 4B FP840K / 5.2 GB1466723
Qwen3 4B40K / 8.1 GB173198
Jan Nano40K / 8.1 GB5435
Note: green Score (e.g. "73.2") means that the model is better than ertghiu256/qwen3-4b-code-reasoning.

Rank the Qwen3 4B Code Reasoning Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 49328 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124