can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run Llama 3.1 8B?

Llama · Llama 3.1 Community · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.1 8B at Q8_0 · 8.5 GB · 189–284 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K2.6 GB277–415 tok/sRuns great
Q3_K_M3.5 GB260–389 tok/sRuns great
Q4_K_M4.9 GB235–353 tok/sRuns great
Q5_K_M5.7 GB223–334 tok/sRuns great
Q6_K6.6 GB211–316 tok/sRuns great
Q8_08.5 GB189–284 tok/sRuns great

Ran Llama 3.1 8B on a NVIDIA H200 (141GB)? Add your real numbers →