Can I Run Aya Expanse on Mac Studio (M3 Ultra, 256 GB)?

Written by Jakub Rusinowski · Last updated October 8, 2024

Yes — comfortably

Yes, comfortably — Aya Expanse 32B at Q8_0 needs about 36.5 GB of the 192 GB usable on Mac Studio (M3 Ultra, 256 GB), leaving ~155.5 GB spare and running at ~12.4 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~12.4 tok/s

Mac Studio (M3 Ultra, 256 GB) — what it gives a model

Usable memory for models192 GB
Memory bandwidth819 GB/s
Form factorDesktop
Operating systemmacOS
Memory upgradeableNo — soldered

Aya Expanse on Mac Studio (M3 Ultra, 256 GB): memory by quantization

QuantMemory neededFits 192 GB?Max contextEst. speedDownload
F1666.7 GB✓ Yes64K~6.7 tok/s64.6 GB
Q8_036.5 GB✓ Yes64K~12.4 tok/s34.3 GB
Q6_K28.6 GB✓ Yes64K~15.7 tok/s26.5 GB
Q5_K_M25 GB✓ Yes64K~18 tok/s22.9 GB
Q4_K_M21.6 GB✓ Yes64K~20.9 tok/s19.5 GB
Q3_K_M15.9 GB✓ Yes64K~28.4 tok/s13.8 GB
Q2_K12.8 GB✓ Yes64K~35.5 tok/s10.6 GB

Which Aya Expanse sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Aya Expanse 32B21.6 GB✓ Fits~20.9 tok/s
Aya Expanse 8B6.7 GB✓ Fits~66.7 tok/s

What to watch out for

Mac Studio M3 Ultra 256 GB limitations

Recommended setup

Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput

How these numbers are calculated

FAQ

Can I run Aya Expanse on Mac Studio (M3 Ultra, 256 GB)?

Yes, comfortably — Aya Expanse 32B at Q8_0 needs about 36.5 GB of the 192 GB usable on Mac Studio (M3 Ultra, 256 GB), leaving ~155.5 GB spare and running at ~12.4 tok/s (estimated), with room for about 65,536 tokens of context.

Which quantization of Aya Expanse should I use on Mac Studio (M3 Ultra, 256 GB)?

Q8_0 — it needs about 36.5 GB of the 192 GB available, downloads as roughly 34.3 GB, and runs at an estimated 12.4 tokens/sec with up to 64K of context.

What limits Aya Expanse on Mac Studio (M3 Ultra, 256 GB)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput

Other Computers

Other Models on Mac Studio (M3 Ultra, 256 GB)

Aya Expanse on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Aya Expanse model page | Check your hardware