can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI300X (192GB) run Ornith 1.0 9B?

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

Yes — it runs great.

Best fit: Ornith 1.0 9B at FP16 · 17.9 GB · 134–202 tok/s on a AMD Instinct MI300X (192GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M5.6 GB233–349 tok/sRuns great
Q5_K_M6.5 GB221–332 tok/sRuns great
Q6_K7.4 GB211–316 tok/sRuns great
Q8_09.5 GB189–283 tok/sRuns great
FP1617.9 GB134–202 tok/sRuns great

Ran Ornith 1.0 9B on a AMD Instinct MI300X (192GB)? Add your real numbers →