Proof in production.
Explore real-world deployments and benchmarks — where the Bud platform delivered measured performance and cost results across Intel, AMD, and NVIDIA hardware, from sovereign language models to enterprise RAG.
Explore the collection.
Each case study is a complete, self-contained read. Select any title to explore it in full.
Hex-1: India's first open-source Indic LLM
Bud Ecosystem built Hex-1 — a 4-billion-parameter open-source LLM for Indic languages — with AMD. Trained on AMD Instinct™ MI300X GPUs and the ROCm™ stack, it reaches state-of-the-art performance in Hindi, Telugu, and more.
Read the case studyEnhancing LLM inference on Intel CPUs
Bud Runtime turned CPU-based LLM inference from impractical into production-ready — lifting throughput from 9 to 520 tokens per second on 4th Gen Intel® Xeon® Scalable Processors with AMX, via custom kernels and deep memory and attention optimization.
Read the case studyBenchmarking Mistral 7B inference on GPUs
A head-to-head evaluation of three inference engines — vLLM, TGI, and Bud Runtime — serving Mistral 7B on an NVIDIA A100 80GB GPU. Bud Runtime delivered the highest throughput and the lowest execution time.
Read the case studyBenchmarking Project Indus on Intel AI hardware
An open-source 1.2-billion-parameter language model for Hindi and its 37 dialects, served on 5th Gen Intel® Xeon® processors with Bud Runtime — delivering GPU-class inference performance on CPUs, without the GPU.
Read the case studyDriving enterprise RAG innovation on Intel Xeon
Bud Ecosystem, FoundationFlow, and Intel built a custom Retrieval-Augmented Generation chatbot for product-catalogue support — running on Intel® Xeon® processors with the BudServe engine. GPU-comparable performance on CPU, with roughly 60% lower cost.
Read the case studyPut your data on it.
The fastest way to see what an integrated AI operating system does for your enterprise is a proof-of-concept on your infrastructure, with your data.