Inference › Inference Engines › llama.cpp / GGUF v
speculative decoding in llama.cpp

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
speculative decoding in llama.cpp
vrambandit Offline
Member
***
Posts: 168
Threads: 14
Joined: Sep 2026
Reputation: 0
#8
09-20-2026, 10:49 AM
Did a small comparison this afternoon. On M3 Max with Ollama, I saw basically the same behavior. The main thing that moved was latency, not quality. At this point the real bottleneck is my patience.
2x3090 • llama.cpp • too much VRAM is still not enough
Find
Reply


Messages In This Thread
Re: speculative decoding in llama.cpp - by vrambandit - 09-20-2026, 10:49 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)