can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H100 SXM (80GB) run MiMo V2.6 Distill Qwen 9B?

MiMo · MIT · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: MiMo V2.6 Distill Qwen 9B at FP16 · 17.9 GB · 100–150 tok/s on a NVIDIA H100 SXM (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.6 GB235–353 tok/sRuns great
Q3_K_M4.5 GB218–327 tok/sRuns great
Q4_K_M5.8 GB195–292 tok/sRuns great
Q5_K_M6.9 GB180–270 tok/sRuns great
Q6_K7.8 GB169–253 tok/sRuns great
Q8_09.6 GB151–226 tok/sRuns great
FP1617.9 GB100–150 tok/sRuns great
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsMiMo V2.6 Distill Qwen 9B on other machinesWhat to buy to run it →

Ran MiMo V2.6 Distill Qwen 9B on a NVIDIA H100 SXM (80GB)? Add your real numbers →