← Back to feed

Celeris-1: A diffusion LLM benchmarked at 2,082 output tokens/s

AI · Technology · 2026-08-05 06:54:00

Celeris-1 achieves 2,082 tokens/s in diffusion LLM benchmark, showcasing its prowess in large-scale text generation.

Source: artificialanalysis.ai

Auto-generated summary for reference only. RSS