SambaNova's heterogeneous compute platform achieves 763 tok/s on MiniMax M2.7 using H200s and SN50 RDUs

Jul 10, 2026

Third-party benchmarks show SambaNova's platform, which combines Nvidia H200 GPUs and its own SN50 RDUs, delivers 763 tokens per second on the MiniMax M2.7 model. This result demonstrates the potential of heterogeneous computing for AI inference workloads.

Why it matters: This benchmark suggests a way to improve inference performance by leveraging both new and existing hardware.

Full story at: The Register / AI & ML ↗