Character.ai, #AMD, & #DigitalOcean are scaling the Qwen3-235B open-weight Mixture-of-Experts AI model to serve approximately 20M users. 📈☁️🤖 FP8 inference and a 5600/140 (ISL/OSL) workload on AMD Instinct™ MI325X GPUs maximize request throughput (QPS). 🔗 https://do.co/4aSNHAN

1 likes 0 replies