can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H100 SXM (80GB) run Ornith 1.5 35B-A3B (MoE)?

Ornith · MIT · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 35B-A3B (MoE) at Q8_0 · 37.8 GB · 247–370 tok/s on a NVIDIA H100 SXM (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB312–467 tok/sRuns great
Q3_K_M16.7 GB300–450 tok/sRuns great
Q4_K_M21.9 GB285–428 tok/sRuns great
Q5_K_M25.5 GB275–413 tok/sRuns great
Q6_K30.5 GB263–394 tok/sRuns great
Q8_037.8 GB247–370 tok/sRuns great
FP1671.1 GB193–289 tok/sTight / slow

Ran Ornith 1.5 35B-A3B (MoE) on a NVIDIA H100 SXM (80GB)? Add your real numbers →