SemiAnalysis: Nvidia up to 5x more cost-efficient than AMD due to software gap
rohanpaul_ai · x · 2026-08-25
A new SemiAnalysis report indicates Nvidia achieves up to 5x better cost efficiency than AMD at 150 tok/s/user in an SGLang comparison. The report concludes that even if AMD hardware were free, Nvidia's total cost per token remains lower due to the current state of AMD's software stack.
Related event: SemiAnalysis: NVIDIA Leads AMD by Up to 5x in Inference Cost Efficiency(2 posts)→
More from Infra
- SK Hynix ties new US plant to looser chip equipment exports to China, sources say — pstAsiatech · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15