Posts by Chaitanya Manem
Building a State-of-the-Art 32 Billion Reasoning Model with Only Synthetic Data on AMD GPUs
- 06 December 2025
Building a state-of-the-art reasoning model is often viewed as a resource-heavy marathon requiring massive compute, months of training, and proprietary datasets. In this blog, we demonstrate how we built a large reasoning model on AMD Instinct™ MI325 GPUs that surpasses the accuracy of the top 32 Billion sized open models on mathematics and science benchmarks, using only synthetic data and with standard Supervised Fine-Tuning (SFT) on top of older-generation models. In line with AMD’s commitment to open source, we are releasing the model weights, detailed training configurations, datasets, and code, enabling the AI community to collaborate, replicate, and innovate, thereby accelerating progress.
Introducing Instella: New State-of-the-art Fully Open 3B Language Models
- 05 March 2025
AMD is excited to announce Instella, a family of fully open state-of-the-art 3-billion-parameter language models (LMs) trained from scratch on AMD Instinct™ MI300X GPUs. Instella models outperform existing fully open models of similar sizes and achieve competitive performance compared to state-of-the-art open-weight models such as Llama-3.2-3B, Gemma-2-2B, and Qwen-2.5-3B, including their instruction-tuned counterparts.