Skip to content
can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro M3 Pro (18GB) run GPT-OSS 20B (MoE)?

GPT-OSS · Apache 2.0 · estimated for a 18.0 GB machine at 4K context.

Yes, but it's tight.

Tight / slow

Best fit: GPT-OSS 20B (MoE) at Q4_K_M · 11.6 GB weights · 38–56 tok/s on a MacBook Pro M3 Pro (18GB).

Arena Text Overall · style-controlled

1,317Q4_K_M untested

gpt-oss-20b · published configuration reference · Q4_K_M not tested

Arena Text Overall (style-controlled), exact published entry gpt-oss-20b, 2026-10-08: reference rating 1,317.3. Published confidence bounds 1,310.9–1,323.8. 10,418 votes. Published gpt-oss-20b configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected Q4_K_M has not been measured by this Arena entry. No quantization quality adjustment is applied.

Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh

Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986

Total memory at 4K context
12.5 GB
Weights + KV cache + runtime overhead
Estimated generation
38–56 tok/s
Estimated first token
~6.9s

Every quantization on this machine

On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.

GPT-OSS 20B (MoE) quantizations on MacBook Pro M3 Pro (18GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K11.5 GB12.4 GB38–57 tok/sTight / slow
Q3_K_M11.5 GB12.4 GB38–57 tok/sTight / slow
Q4_K_M11.6 GB12.5 GB38–56 tok/sTight / slow
Q5_K_M11.7 GB12.6 GB— not residentWon't fit
Q6_K12.0 GB12.9 GB— not residentWon't fit
Q8_012.1 GB13.0 GB— not residentWon't fit
FP1613.8 GB14.7 GB— not residentWon't fit

Ran GPT-OSS 20B (MoE) on a MacBook Pro M3 Pro (18GB)? Add your real numbers →