can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4060 Ti (16GB) run Ornith 1.5 35B-A3B (MoE)?

Ornith · MIT · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Ornith 1.5 35B-A3B (MoE) at Q2_K · 13.1 GB · 120–180 tok/s on a NVIDIA RTX 4060 Ti (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB120–180 tok/sTight / slow
Q3_K_M16.7 GB102–153 tok/sWon't fit
Q4_K_M21.9 GB84–127 tok/sWon't fit
Q5_K_M25.5 GB75–113 tok/sWon't fit
Q6_K30.5 GB65–98 tok/sWon't fit
Q8_037.8 GB55–83 tok/sWon't fit
FP1671.1 GB32–48 tok/sWon't fit

Ran Ornith 1.5 35B-A3B (MoE) on a NVIDIA RTX 4060 Ti (16GB)? Add your real numbers →