can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run Ornith 1.0 35B (MoE)?

Ornith · MIT · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.0 35B (MoE) at FP16 · 69.4 GB · 266–399 tok/s on a AMD Instinct MI355X (288GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB343–514 tok/sRuns great
Q3_K_M16.7 GB335–503 tok/sRuns great
Q4_K_M22.1 GB326–490 tok/sRuns great
Q5_K_M26.5 GB320–480 tok/sRuns great
Q6_K29.3 GB316–473 tok/sRuns great
Q8_036.9 GB305–457 tok/sRuns great
FP1669.4 GB266–399 tok/sRuns great

Ran Ornith 1.0 35B (MoE) on a AMD Instinct MI355X (288GB)? Add your real numbers →