can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run Ornith 1.5 35B-A3B (MoE)?

Ornith · MIT · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 35B-A3B (MoE) at FP16 · 71.1 GB · 225–338 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB326–490 tok/sRuns great
Q3_K_M16.7 GB318–476 tok/sRuns great
Q4_K_M21.9 GB306–458 tok/sRuns great
Q5_K_M25.5 GB298–447 tok/sRuns great
Q6_K30.5 GB287–431 tok/sRuns great
Q8_037.8 GB274–411 tok/sRuns great
FP1671.1 GB225–338 tok/sRuns great

Ran Ornith 1.5 35B-A3B (MoE) on a NVIDIA H200 (141GB)? Add your real numbers →