Ling-3.0-flash-dspark open-sourced, hits 1,120 tok/s on 4 Blackwell GPUs
AdinaYakup · x · 2026-08-22
Ling-3.0-flash-dspark, a DSpark draft model built for Ling-3.0-flash, is now open-sourced. On 4 NVIDIA Blackwell GPUs at batch 1, it delivered 1,120 tok/s, 0.78 ms mean TPOT, and an accept length of 9.95 across 1,000 requests.
More from Models
- Developer feedback: Instinct is interesting but ultimately uninteresting — signulll · 2026-08-22
- Ling-3.0 releases checkpoints across three training stages — Designer_Mouse_6109 · 2026-08-22
- Mysterious 'Ox Alpha' model offers 1M context, huge compute claims — udmrzn · 2026-08-22
- Surprisingly hard to finetune models to avoid unnecessary hyphens — ivan_bezdomny · 2026-08-22
- Hands-on: Qwen3.8-27B Q6 Delivers Strong Agentic Coding Performance — Ok_Ninja7526 · 2026-08-22
- User test finds AI stereotypes about Jews are relatively tame — doodlestein · 2026-08-22