Back
Ssignal
17
·10 days ago·1 signals
Archived topic · source no longer tracked

After pushing 1M+ tokens through Qwen 3.8 27B, here is my optimal llama.cpp config for 16GB VRAM (73k Context, Agentic Coding)

LlamaQwenNVIDIAOn-device

Heat trend

Collecting trend data

The percentage is based on available heat signal, not comment count or independent people.