can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3080 (10GB) run Ornith 1.5 9B?

Ornith · MIT · estimated for a 10.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 9B at Q5_K_M · 6.9 GB · 66–99 tok/s on a NVIDIA RTX 3080 (10GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB98–147 tok/sRuns great
Q3_K_M4.9 GB85–128 tok/sRuns great
Q4_K_M5.9 GB74–111 tok/sRuns great
Q5_K_M6.9 GB66–99 tok/sRuns great
Q6_K7.7 GB60–90 tok/sTight / slow
Q8_09.6 GB50–75 tok/sWon't fit
FP1617.9 GB29–43 tok/sWon't fit

Ran Ornith 1.5 9B on a NVIDIA RTX 3080 (10GB)? Add your real numbers →