Tencent releases Qwen3.8-27B-DSpine: a 27B draft model for speculative decoding
tencent · hf · 2026-11-07
Tencent published Qwen3.8-27B-DSpine-b16 on Hugging Face, a 27B text-generation model based on Qwen/Qwen3.8-27B, positioned as a draft model for speculative decoding.
Released in safetensors format with sglang support, it's tied to two arXiv papers describing the DSpine approach, aiming to accelerate large-model inference.
Related event: Tencent Open-Sources DSpine Draft Model, Speeding Up 27B Inference by 3x(4 posts)→
More from Models
- Kimi and 1017 are closer in performance than they appear, and both trail the frontier — teortaxesTex · 2026-11-10
- Polymarket odds of "Fable" launching today surge to 70% — spreadlove5683 · 2026-11-10
- Congress returns to session with expected focus on OpenAI rogue model incidents — peterwildeford · 2026-11-10
- "Benchmarks rule out the bad models — the good ones I test on my own work" — ChemicalExcellent463 · 2026-11-10
- Elon Musk amplifies Grok Bot feedback thread as team works on token efficiency fixes — elonmusk · 2026-11-10
- PostTrainBench v1.2: Gemini 4 Argon Scores 40.4% (#5), Muse Wonder 24.2% (#17) — maksym_andr · 2026-11-09