AMD MI355X out-earns Nvidia B200 by 61% serving MiniMax M3
AnushElangovan · x · 2026-10-02
An inference economics analysis claims AMD's MI355X out-earns Nvidia's B200 when serving MiniMax M3: $6.21 vs $3.86 (+61%) at 65 tok/s, and $2.52 vs $1.63 (+55%) at 150 tok/s. Even more striking, GB300/GB200 NVL72 reportedly lose money on the same workload.
More from Infra
- huggingface_hub v2.1.0 ships: 17x faster downloads, job retries, rerun and port exposure — huggingface · 2026-10-02
- Infra engineers compare notes on when self-hosting LLMs beats paying for APIs — One_Mention_5385 · 2026-10-02
- Gemini 4 isn't even out yet — but Google's TPU advantage is being underappreciated — haider1 · 2026-10-02
- parakeet_cuda: local Parakeet transcription on a 2GB VRAM GTX 750 Ti, ~20x realtime — mgostIH · 2026-10-02
- Sentdex gets hands on Asus ET900N G3, the GB300-based DGX Station — Sentdex · 2026-10-02
- Bittensor's iota productizes decentralized training with pipeline parallelism — markjeffrey · 2026-10-02