Ssignal
18
·4 days ago·1 signals
Archived topic · source no longer tracked
I benchmark DFlash 2 (PR build) in llama.cpp on Qwen 3.8 27B against all speculative methods for 3 days. 2.26x on 100 real coding prompts, 4.68x with one n-gram drafter on top. Up to 8x on specific cases.
Heat trend
Collecting trend data
The percentage is based on available heat signal, not comment count or independent people.
Llama model activity is surfacing — worth tracking for capability changes, ecosystem impact, and availability.