can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run GPT-OSS 20B (MoE)?

GPT-OSS · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GPT-OSS 20B (MoE) at FP16 · 13.8 GB · 214–321 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.5 GB229–343 tok/sRuns great
Q3_K_M11.5 GB229–343 tok/sRuns great
Q4_K_M11.6 GB228–342 tok/sRuns great
Q5_K_M11.7 GB227–341 tok/sRuns great
Q6_K12.0 GB225–338 tok/sRuns great
Q8_012.1 GB225–337 tok/sRuns great
FP1613.8 GB214–321 tok/sRuns great

Ran GPT-OSS 20B (MoE) on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →