can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI300X (192GB) run Ornith 1.5 9B?

Ornith · MIT · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 9B at FP16 · 17.9 GB · 136–204 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB263–395 tok/sRuns great
Q3_K_M4.9 GB249–373 tok/sRuns great
Q4_K_M5.9 GB234–351 tok/sRuns great
Q5_K_M6.9 GB222–333 tok/sRuns great
Q6_K7.7 GB212–317 tok/sRuns great
Q8_09.6 GB192–288 tok/sRuns great
FP1617.9 GB136–204 tok/sRuns great

Ran Ornith 1.5 9B on a AMD Instinct MI300X (192GB)? Add your real numbers →