can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Ornith 1.5 9B?

Ornith · MIT · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 9B at FP16 · 17.9 GB · 61–92 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB170–254 tok/sRuns great
Q3_K_M4.9 GB153–229 tok/sRuns great
Q4_K_M5.9 GB137–206 tok/sRuns great
Q5_K_M6.9 GB125–187 tok/sRuns great
Q6_K7.7 GB116–173 tok/sRuns great
Q8_09.6 GB100–149 tok/sRuns great
FP1617.9 GB61–92 tok/sRuns great

Ran Ornith 1.5 9B on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →