can-i-run-this-llm

Can I run this LLM?

Can a MacBook Pro / Mac Studio M4 Max (128GB) run Qwen3.8 Flash Next (MoE)?

Qwen · See model card · estimated for a 128.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Qwen3.8 Flash Next (MoE) at Q2_K · 80.9 GB · 74–110 tok/s on a MacBook Pro / Mac Studio M4 Max (128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K80.9 GB74–110 tok/sTight / slow
Q3_K_M92.0 GB69–103 tok/sWon't fit
Q4_K_M119.6 GB58–88 tok/sWon't fit
Q5_K_M134.7 GB54–81 tok/sWon't fit
Q6_K168.1 GB46–69 tok/sWon't fit
Q8_0188.3 GB43–64 tok/sWon't fit
FP16354.0 GB26–39 tok/sWon't fit
Open the full calculator →Everything a MacBook Pro / Mac Studio M4 Max (128GB) runsQwen3.8 Flash Next (MoE) on other machinesWhat to buy to run it →

Ran Qwen3.8 Flash Next (MoE) on a MacBook Pro / Mac Studio M4 Max (128GB)? Add your real numbers →