can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air M2 (24GB) run Gemma 4 26B-A4B (MoE)?

Gemma · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Gemma 4 26B-A4B (MoE) at Q3_K_M · 12.7 GB · 25–37 tok/s on a MacBook Air M2 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M12.7 GB25–37 tok/sRuns great
Q4_K_M17.0 GB20–30 tok/sWon't fit
Q5_K_M21.2 GB17–25 tok/sWon't fit
Q6_K23.2 GB15–23 tok/sWon't fit
Q8_026.9 GB14–20 tok/sWon't fit
FP1650.5 GB8–12 tok/sWon't fit
Open the full calculator →Everything a MacBook Air M2 (24GB) runsGemma 4 26B-A4B (MoE) on other machinesWhat to buy to run it →

Ran Gemma 4 26B-A4B (MoE) on a MacBook Air M2 (24GB)? Add your real numbers →