State-of-the-art Small Language Coder Model: Mify-Coder
Abhinav Parmar, Abhisek Panigrahi, Abhishek Kumar Dwivedi, Abhishek Bhattacharya, Adarsh Ramachandra, Aditya Choudhary, Aditya Garg, Aditya Raj, Alankrit Bhatt, Alpesh Yadav, Anant Vishnu, Ananthu Pillai, Ankush Kumar, Aryan Patnaik, Aswatha Narayanan S, Avanish Raj Singh, Bhavya Shree Gadda, Brijesh Pankajbhai Kachhadiya, Buggala Jahnavi, Chidurala Nithin Krishna, Chintan Shah, Chunduru Akshaya, Debarshi Banerjee, Debrup Dey, Deepa R., Deepika B G, Faiz ur Rahman, Gagan Gayari, Gudhi Jagadeesh Kumar Naidu, Gursimar Singh, Harshal Tyagi, Harshini K, James Mani Vathalloor, Jayarama Nettar, Jayashree Gajjam, Joe Walter Sugil George, Kamalakara Sri Krishna Tadepalli, Kamalkumar Rathinasamy, Karan Chaurasia, Karthikeyan S, Kashish Arora, Kaushal Desai, Khushboo Buwade, Kiran Manjrekar, Malikireddy Venkata Sai Likhitha, Manjunath A, Mitali Mahavir Bedmutha, Mohammed Rafee Tarafdar, Nikhil Tiwari, Nikitha K Gigi, Pavan Ravikumar, Pendyala Swarnanjali, Piyush Anand, Prakash Chandrasekar, Prasanna Bhalchandra Gawade, Prasanth Sivan, Preeti Khurana, Priyanshi Babbar, Rajab Ali Mondal, Rajesh Kumar Vissapragada, Rajeshwari Ganesan, Rajeswari Koppisetti, Ramjee R., Ramkumar Thiruppathisamy, Rani G. S., S Reka, Samarth Gupta, Sandeep Reddy Kothakota, Sarathy K, Sathyanarayana Sampath Kumar, Saurabh Kumar, Shashank Khasare, Shenbaga Devi Venkatesh Kumar, Shiva Rama Krishna Parvatham, Shoeb Shaikh, Shrishanmathi A, Shubham Pathak, Sree Samhita Koppaka, Sreenivasa Raghavan K S, Sreeram Venkatasubramanian, Suprabha Desai Bojja, Swetha R, Syed Ahmed, Chinmai Harshitha Thota, Tushar Yadav, Veeravelly Kusumitha, V V S S Prasanth Patnaik, Vidya Sri Sesetti, Vijayakeerthi K, Vikram Raj Bakshi, Vinay K K, Vinoth Kumar Loganathan, Vipin Tiwari, Vivek Kumar Shrivastav, V Venkata Sri Datta Charan, Wasim Akhtar Khan
TL;DR
Mify-Coder demonstrates that a 2.5B-parameter code model, when trained with a compute-optimal CPT-SFT pipeline and disciplined data curation, can match or exceed frontier models on standard coding benchmarks while maintaining enterprise-grade safety. The approach integrates high-quality real and synthetic data, rigorous decontamination, and alignment at scale, complemented by FP8 quantization for CPU-friendly deployment. Across code generation and function calling tasks, Mify-Coder achieves top MBPP performance and competitive HumanEval results, with low-latency inference on high-end GPUs and scalable CPU inference through quantization. These results challenge scale-centric assumptions and show that careful data, training, and alignment strategies can deliver practical, high-performing, resource-efficient coding LLMs for real-world software development workflows.
Abstract
We present Mify-Coder, a 2.5B-parameter code model trained on 4.2T tokens using a compute-optimal strategy built on the Mify-2.5B foundation model. Mify-Coder achieves comparable accuracy and safety while significantly outperforming much larger baseline models on standard coding and function-calling benchmarks, demonstrating that compact models can match frontier-grade models in code generation and agent-driven workflows. Our training pipeline combines high-quality curated sources with synthetic data generated through agentically designed prompts, refined iteratively using enterprise-grade evaluation datasets. LLM-based quality filtering further enhances data density, enabling frugal yet effective training. Through disciplined exploration of CPT-SFT objectives, data mixtures, and sampling dynamics, we deliver frontier-grade code intelligence within a single continuous training trajectory. Empirical evidence shows that principled data and compute discipline allow smaller models to achieve competitive accuracy, efficiency, and safety compliance. Quantized variants of Mify-Coder enable deployment on standard desktop environments without requiring specialized hardware.