can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air M2 (24GB) run Qwen3.5 4B?

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

Yes — it runs great.

Best fit: Qwen3.5 4B at Q8_0 · 4.5 GB · 12–19 tok/s on a MacBook Air M2 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q3_K_M1.8 GB25–37 tok/sRuns great
Q4_K_M2.6 GB19–29 tok/sRuns great
Q5_K_M3.0 GB17–26 tok/sRuns great
Q6_K3.5 GB15–23 tok/sRuns great
Q8_04.5 GB12–19 tok/sRuns great
FP168.4 GB7–11 tok/sTight / slow

Ran Qwen3.5 4B on a MacBook Air M2 (24GB)? Add your real numbers →