can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5060 (8GB) run Ternary Bonsai 2 27B?

Bonsai · Apache 2.0 · estimated for a 8.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Ternary Bonsai 2 27B at PTQ1_0 · 6.0 GB · 34–51 tok/s on a NVIDIA RTX 5060 (8GB).

Every quantization on this machine

QuantSizeSpeedFit
PTQ1_06.0 GB34–51 tok/sTight / slow
PQ2_07.2 GB32–49 tok/sWon't fit

Ran Ternary Bonsai 2 27B on a NVIDIA RTX 5060 (8GB)? Add your real numbers →