Ling-3.0-flash

0–100 · higher means more positive community experience, not benchmark performance.

Updated 2026-09-05 14:21 UTC · 2026-08-29 – 2026-09-05 UTC

Community scoreCollecting reviews2 comments in 7 days

Community reviews

Selected comments from the last 7 days. The balance of excerpts does not represent the share of positive reviews.

1 selected excerpts

PositiveSpeed & latency2026-09-02

“Single request decoding went from 288 tok/s to 606 tok/s, paired with the newly released DSpark draft model, reaching 1120 tok/s, with an average latency of 0.78ms per token”

ZhihuzhMachine translated

Show original

单请求解码从288 tok/s拉到606 tok/s，配上新发布的DSpark草稿模型，干到1120 tok/s，平均每token延迟0.78毫秒