§ qwen · storyline
Hosting Qwen on Blackwell
Perplexity details its inference setup for serving Qwen3 235B models on NVIDIA Blackwell GPUs, optimising for cost and performance.
Details Perplexity's inference setup for serving post-trained Qwen3 235B models on NVIDIA Blackwell GPUs, optimizing for cost and performance.
§ sources1 publication · timeline below
- research.perplexity.aiHosting Qwen on Blackwellprimary