can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run Ornith 1.5 35B-A3B (MoE)?

Ornith · MIT · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 35B-A3B (MoE) at FP16 · 71.1 GB · 26–39 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K13.1 GB81–122 tok/sRuns great
Q3_K_M16.7 GB72–107 tok/sRuns great
Q4_K_M21.9 GB61–92 tok/sRuns great
Q5_K_M25.5 GB56–83 tok/sRuns great
Q6_K30.5 GB49–74 tok/sRuns great
Q8_037.8 GB42–63 tok/sRuns great
FP1671.1 GB26–39 tok/sRuns great

Ran Ornith 1.5 35B-A3B (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →