IQ2_M on a 16 GB 5060 Ti. Claimed 10 tok/s.
Params
27B
Fastest decode
10 tok/s
RTX 5060 Ti 16GB · IQ2_M GGUF · llama.cpp
Setups
1
Best reported pair · not live serving speed ↗
Runs on
Quoted one-stream decode on real boxes.
No public weights link on this desk yet.
