can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5090 (32GB) run Ornith 1.0 9B?

Ornith · MIT · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.0 9B at FP16 · 17.9 GB · 60–90 tok/s on a NVIDIA RTX 5090 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M5.6 GB135–203 tok/sRuns great
Q5_K_M6.5 GB125–187 tok/sRuns great
Q6_K7.4 GB115–173 tok/sRuns great
Q8_09.5 GB97–145 tok/sRuns great
FP1617.9 GB60–90 tok/sRuns great

Ran Ornith 1.0 9B on a NVIDIA RTX 5090 (32GB)? Add your real numbers →