aicanrun

Can Qwen 3.6 35B-A3B run on MacBook Air M1 8GB?

NO — Won’t fit
Q4_K_M · 4K context · formula estimate

What this means

The checked Q4_K_M build needs about 24.1GB, above this Mac's conservative 5GB working budget.

View technical details ↓

−19.1GB short
above the working budget
24.1GB
needed at Q4_K_M
Q4_K_M
quant selected
0GB
working headroom
needs 24.1 GBworking budget 5 GB · short 19.1 GB
Apple M18 GB unified memoryMetalFanless

Where the memory goes

ComponentDetailGB
Model weightsQ4_K_M GGUF (22.1 GB) + mmap overhead23.2
KV cache4K context window0.1
RuntimemacOS inference app + compute buffers0.8
Total neededQ4_K_M, 4K context24.1
Working budget8 GB unified memory − conservative macOS reserve5
Headroommemory shortfall−19.1

Pick your quant

QuantDownloadMemoryEstimated speedVerdict
Q3_K_M16.6 GB18.3 GB—✕ Won't fit
IQ4_XS17.7 GB19.5 GB—✕ Won't fit
Q4_K_S20.9 GB22.8 GB—✕ Won't fit
MXFP421.7 GB23.7 GB—✕ Won't fit
Q4_K_M ★22.1 GB24.1 GB—✕ Won't fit
Q5_K_M26.5 GB28.7 GB—✕ Won't fit
Q6_K29.3 GB31.6 GB—✕ Won't fit
Q8_036.9 GB39.6 GB—✕ Won't fit

Other models on this Mac

Ternary Bonsai 4B · Q2_0Llama 3.2 3B · Q4_K_MSmolLM3 3B · Q4_K_MMinistral 3 3B · Q4_K_MG9v3 3B · Q4_K_MQwen 3.5 2B · Q4_K_M

Qwen 3.6 35B-A3B on other MacBook Air M1 configurations

Check 16GB

FAQ

Can the MacBook Air M1 · 8GB run Qwen 3.6 35B-A3B?

Not with the quants currently tracked. The selected Q4_K_M build needs about 24.1GB, above the 5GB working budget.

Which Qwen 3.6 35B-A3B quant should I use on this Mac?

None of the tracked quants fit this configuration safely. Choose a smaller model or a Mac with more unified memory.

Which app should I use for Qwen 3.6 35B-A3B on this Mac?

Start with LM Studio. This page gives the complete point-and-click walkthrough.

Are these speeds measured on a MacBook Air M1?

No. The range is a formula estimate based on memory bandwidth, model size, active parameters, cooling, and a 4K context. The app, backend, thermals, and prompt can change real performance.