can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4080 (16GB) run GPT-OSS 20B (MoE)?

GPT-OSS · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: GPT-OSS 20B (MoE) at Q5_K_M · 11.7 GB · 145–217 tok/s on a NVIDIA RTX 4080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K11.5 GB146–219 tok/sRuns great
Q3_K_M11.5 GB146–219 tok/sRuns great
Q4_K_M11.6 GB145–218 tok/sRuns great
Q5_K_M11.7 GB145–217 tok/sRuns great
Q6_K12.0 GB142–214 tok/sTight / slow
Q8_012.1 GB142–213 tok/sTight / slow
FP1613.8 GB132–198 tok/sWon't fit

Ran GPT-OSS 20B (MoE) on a NVIDIA RTX 4080 (16GB)? Add your real numbers →