NVIDIA demos 2,529 output tokens per second for Qwen 27B at GTC
IanAndrewsDC · x · 2026-09-28
NVIDIA's Ian Buck took the stage at a GTC event, reporting inference performance of 2,529 output tokens per second for Qwen 3.8 27B. The figure drew attention from folks at SemiAnalysis, Cerebras, and Inferact, offering a benchmark point for comparing inference-stack throughput across providers.
More from Infra
- Sarvam AI Launches Token Factory: India-Hosted Inference for Open Models — itsOmSarraf_ · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Jailbroken PS4 runs a 9B open-source model at up to 43 tok/s by talking directly to its 2013-era GPU — AIFlow_ML · 2026-11-16
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16
- Stratechery's Fictional Obituary: Imagining Jensen Huang's 2026 Exit From Nvidia — Gregory_C_Allen · 2026-11-16
- vLLM serves DeepSeek V4.1-Flash at 954K tokens/s per GPU, $38.96/GPU-hour on GB300 NVL72 — bookwormengr · 2026-11-16