AMD MI355X posts fastest single-user inference, ~2.4x H200 tokens per dollar in tests
AryHHAry · x · 2026-11-11
PerchTerminal reports that in its testing AMD's MI355X delivered the fastest single-user inference speed of anything tested and roughly 2.4x H200's tokens per dollar, with 100B+ tokens already run on the cards — prompting the question of why AMD gets so little attention. NVIDIA's Anush Elangovan amplified the post.
More from Infra
- Liquid AI models are already running in Mercedes-Benz cars, phones next — agihouse_org · 2026-11-11
- AGI House:本地芯片 AI 能力仅用了 10-15%,应用是最大短板 — agihouse_org · 2026-11-11
- HF tokenizers v1.0.0-rc.4 restores Python APIs and encodes up to 17x faster — art_zucker · 2026-11-11
- MacPaw's Elix claims fastest LLM inference on Apple silicon, winning all 33 benchmarks — JosephJacks_ · 2026-11-11
- What tasks have you actually moved from cloud models to local ones? — FulcraDynamics · 2026-11-11
- X's recommender is multimodal: CLIP and MultimodalPostEmbedderV5 embeddings feed Phoenix retrieval — cocktailpeanut · 2026-11-11