Can I Run Bonsai 27B on Mac Studio (M2 Ultra, 192 GB)?

Written by Jakub Rusinowski · Last updated July 15, 2026

Yes — comfortably

Yes, comfortably — 1-bit Bonsai 27B at Q8_0 needs about 31.2 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB), leaving ~112.8 GB spare and running at ~14.2 tok/s (estimated), with room for about 262,144 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~14.2 tok/s

See what else this hardware can run →

Buy this hardware NVIDIA GeForce RTX 5090 32GB — 32 GB VRAM · 575 W board power Deploy in the cloud now NVIDIA A40 on RunPod — from $0.44/hr · rate checked 2026-08

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

Bonsai 27B on Mac Studio (M2 Ultra, 192 GB): memory by quantization

Quant	Memory needed	Fits 144 GB?	Max context	Est. speed	Download
F16	56.5 GB	✓ Yes	256K	~7.8 tok/s	54 GB
Q8_0	31.2 GB	✓ Yes	256K	~14.2 tok/s	28.7 GB
Q6_K	24.7 GB	✓ Yes	256K	~18 tok/s	22.1 GB
Q5_K_M	21.7 GB	✓ Yes	256K	~20.6 tok/s	19.1 GB
Q4_K_M	18.8 GB	✓ Yes	256K	~23.7 tok/s	16.3 GB
Q3_K_M	14.1 GB	✓ Yes	256K	~32 tok/s	11.5 GB
Q2_K	11.4 GB	✓ Yes	256K	~39.6 tok/s	8.9 GB

Which Bonsai 27B sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
1-bit Bonsai 27B	18.8 GB	✓ Fits	~23.7 tok/s
Ternary Bonsai 27B	18.8 GB	✓ Fits	~23.7 tok/s

What to watch out for

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Superseded by the M3 Ultra, which is why it is often the better used buy for large-model work.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