thc1006/qwen3.6-speculative-decoding-rtx3090

llama.cpp speculative decoding measured on one RTX 3090, Qwen3.6-35B-A3B UD-Q4_K_XL, commit 3737e4137. Published figures are re-derived from the committed data by a checker that fails on drift, a coverage probe reports how many of them it actually covers, and ERRATA.md lists this study's own retracted claims.

5 best points · 2 comments · 1 Hacker News post · 35 GitHub stars · View on GitHub

Hacker News discussions

• Qwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090 (5 points, 2 comments, by thc1006, 2026-04-21)