can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run Mistral Small 4 119B (MoE)?

Mistral · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Mistral Small 4 119B (MoE) at Q4_K_M · 73.8 GB · 35–52 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M54.4 GB44–66 tok/sRuns great
Q4_K_M73.8 GB35–52 tok/sRuns great
Q5_K_M89.2 GB30–45 tok/sWon't fit
Q6_K99.4 GB28–41 tok/sWon't fit
Q8_0126.5 GB23–34 tok/sWon't fit
FP16238.0 GB13–19 tok/sWon't fit

Ran Mistral Small 4 119B (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →