Can I Run StarCoder 2 on Mac Studio (M3 Ultra, 256 GB)?

Written by Jakub Rusinowski · Last updated February 28, 2024

Yes — comfortably

Yes, comfortably — StarCoder 2 15B at Q8_0 needs about 17.9 GB of the 192 GB usable on Mac Studio (M3 Ultra, 256 GB), leaving ~174.1 GB spare and running at ~24.7 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~24.7 tok/s

See what else this hardware can run →

Buy this hardware AMD Radeon RX 7900 XT 20GB — 20 GB VRAM · 315 W board power Deploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

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

Usable memory for models	192 GB
Memory bandwidth	819 GB/s
Form factor	Desktop
Operating system	macOS
Memory upgradeable	No — soldered

StarCoder 2 on Mac Studio (M3 Ultra, 256 GB): memory by quantization

Quant	Memory needed	Fits 192 GB?	Max context	Est. speed	Download
F16	32.5 GB	✓ Yes	16K	~13.7 tok/s	31 GB
Q8_0	17.9 GB	✓ Yes	16K	~24.7 tok/s	16.5 GB
Q6_K	14.2 GB	✓ Yes	16K	~31.2 tok/s	12.7 GB
Q5_K_M	12.5 GB	✓ Yes	16K	~35.4 tok/s	11 GB
Q4_K_M	10.8 GB	✓ Yes	16K	~40.7 tok/s	9.4 GB
Q3_K_M	8.1 GB	✓ Yes	16K	~54.2 tok/s	6.6 GB
Q2_K	6.6 GB	✓ Yes	16K	~66.2 tok/s	5.1 GB

Which StarCoder 2 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
StarCoder 2 15B	10.8 GB	✓ Fits	~40.7 tok/s
StarCoder 2 7B	5.7 GB	✓ Fits	~75.3 tok/s
StarCoder 2 3B	2.9 GB	✓ Fits	~136.7 tok/s

What to watch out for

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 M3 Ultra 256 GB limitations

The largest single-box unified memory pool available, but at roughly half the memory bandwidth of a high-end discrete GPU — very large models load, then run slowly.
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.
256 GB unified memory at 819 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 computed from this model's published attention configuration.

FAQ