BFL publishes per-GPU benchmarks for FLUX 3 Klein, from 0.59s on DGX Station to 50s on RTX 4070
bfl_ai · x · 2026-10-15
BFL released per-GPU latency benchmarks for FLUX 3 Image Klein: 0.55s per image on GB300 (NVFP4), 4s on RTX 5090 (INT8), and runnable on 8GB VRAM devices. Detailed tables cover DGX Station, RTX PRO 6000/5090/5070/4070 at 1024px and 2048px for both generation and editing, with the 16-step distilled model significantly faster than the 50-step base.
More from Infra
- Dallas Fed: AI data center debt issuance equals ~1/8 of Treasury duration supply — _onionesque · 2026-10-16
- Anthropic ditched Git as agents pushed merges to 30,000 a day, up 10x in 4 months — shashib · 2026-10-16
- NVIDIA ships two Nemotron-3.5 open models in one day: Super for H100, Bolt for RTX — kuchaev · 2026-10-16
- Anthropic now merges 30,000 code changes a day, reviews code by 'intent' not lines — Miles_Brundage · 2026-10-16
- TSMC guides ~$176B revenue for 2026, audits customer buildouts and power before expanding — BenBajarin · 2026-10-16
- Physion Labs unveils NexTron: up to 20.9x SFT throughput vs DeepSpeed on H100 — du_yilun · 2026-10-16