🪽DFlash draft models are available for Ornith-1.5 9B, 35B-A3B, and 397B. DFlash and Ornith 1.5 make a dynamic duo: DFlash performs as the d…

🪽DFlash draft models are available for Ornith-1.5 9B, 35B-A3B, and 397B. DFlash and Ornith 1.5 make a dynamic duo: DFlash performs as the draft model, accelerating inference by drafting multiple tokens at once. Then Ornith 1.5 verifies the draft tokens in one pass instead of generating one token at a time. 👮 We conducted a performance evaluation of the DFlash models. DFlash achieves up to a 2.54× speedup without any loss in generation quality. 🔌 Come and plug this super buddy into your workstation. http://huggingface.co/collections/ornith-ai/ornith-15-dflash

Related

• New Dflash drafting model for the 27b Lets gooooo https://huggingface.co/z-lab/Qwen3.6-27B-DFlash
• DFlash for Kimi-K2.5 was pushed 3 hours ago! Acceptance length varies from 4.0 to 6.3 on datasets. This is only with SGLang btw. https://hug…

Source: Clem Delangue (X) | 2026-09-30