Can I Run Qwen3.8 on Mac Studio (M2 Ultra, 192 GB)?

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026

Yes, but it is tight

Yes, but it is tight — Qwen3.8-Flash-Next at Q5_K_M needs about 131.6 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB), leaving only ~12.4 GB before the runtime starts swapping. Expect ~60.9 tok/s (estimated), with room for about 32,768 tokens of context.

Confidence: low · Recommended quantization: Q5_K_M · Estimated speed: ~60.9 tok/s

Buy This HardwareApple Mac Studio M2 Ultra — 192 GB VRAM · 60 W board power Deploy in the Cloud NowRunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Mac Studio (M2 Ultra, 192 GB) — what it gives a model

Usable memory for models	144 GB
Memory bandwidth	800 GB/s
Form factor	Desktop
Operating system	macOS
Memory upgradeable	No — soldered

Qwen3.8 on Mac Studio (M2 Ultra, 192 GB): memory by quantization

Quant	Memory needed	Fits 144 GB?	Max context	Est. speed	Download
F16	364.1 GB	✗ No	—	—	360 GB
Q8_0	195.3 GB	✗ No	—	—	191.3 GB
Q6_K	151.7 GB	✗ No	—	—	147.6 GB
Q5_K_M	131.6 GB	✓ Yes	32K	~60.9 tok/s	127.6 GB
Q4_K_M	112.7 GB	✓ Yes	64K	~66.8 tok/s	108.7 GB
Q3_K_M	80.8 GB	✓ Yes	128K	~79.7 tok/s	76.7 GB
Q2_K	63.2 GB	✓ Yes	128K	~89.2 tok/s	59.2 GB

Which Qwen3.8 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Qwen3.8-Max	1457.5 GB	✗ Too large	—
Qwen3.8-Flash-Next	112.7 GB	✓ Fits	~66.8 tok/s
Qwen3.8 27B	19.3 GB	✓ Fits	~23.1 tok/s

What to watch out for

1 larger variant of Qwen3.8 does not fit and would need CPU offload or different hardware.
This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.

Mac Studio M2 Ultra 192 GB limitations

Superseded by the M3 Ultra, which is why it is often the better used buy for large-model work.
Memory is soldered; the configuration chosen at purchase is permanent.

Recommended setup

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

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
192 GB unified memory at 800 GB/s, shared between CPU and GPU.
macOS reserves a share of unified memory for the system, so not all of it is available to a model.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is inferred from the parameter count because this model does not publish its full attention configuration.

FAQ