can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run Llama 3.3 70B Instruct?

Llama · Llama 3.3 Community · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.3 70B Instruct at Q8_0 · 75.0 GB · 41–62 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K26.4 GB95–142 tok/sRuns great
Q3_K_M34.3 GB78–117 tok/sRuns great
Q4_K_M42.5 GB66–99 tok/sRuns great
Q5_K_M50.0 GB58–87 tok/sRuns great
Q6_K57.9 GB51–77 tok/sRuns great
Q8_075.0 GB41–62 tok/sRuns great
FP16141.1 GB23–35 tok/sWon't fit

Ran Llama 3.3 70B Instruct on a NVIDIA H200 (141GB)? Add your real numbers →