Can I Run Devstral on Mac mini (M4, 16 GB)?

作者： Jakub Rusinowski · 最后更新： 2026年9月11日

Yes

Yes — Devstral Small 2505 24B at Q2_K needs about 10 GB of the 12 GB usable on Mac mini (M4, 16 GB) (~2 GB spare), at ~7.5 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: high · Recommended quantization: Q2_K · Estimated speed: ~7.5 tok/s

Buy This HardwareIntel Arc B570 10GB — 10 GB VRAM · 150 W board power Deploy in the Cloud NowRTX 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 mini (M4, 16 GB) — what it gives a model

Usable memory for models	12 GB
Memory bandwidth	120 GB/s
Form factor	Mini PC
Operating system	macOS
Memory upgradeable	No — soldered
Price	$599 (lib/data/ai-stations.ts (street price), checked 2026-07-06)

Devstral on Mac mini (M4, 16 GB): memory by quantization

Quant	Memory needed	Fits 12 GB?	Max context	Est. speed	Download
F16	50.1 GB	✗ No	—	—	48 GB
Q8_0	27.6 GB	✗ No	—	—	25.5 GB
Q6_K	21.8 GB	✗ No	—	—	19.7 GB
Q5_K_M	19.2 GB	✗ No	—	—	17 GB
Q4_K_M	16.6 GB	✗ No	—	—	14.5 GB
Q3_K_M	12.4 GB	✗ No	—	—	10.2 GB
Q2_K	10 GB	✓ Yes	16K	~7.5 tok/s	7.9 GB

Which Devstral sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Devstral-2 123B	77.9 GB	✗ Too large	—
Devstral Small 2 24B	17 GB	✗ Too large	—
Devstral Small 2505 24B	16.6 GB	✗ Too large	—
Devstral-2 22B (Unverified Listing)	15.7 GB	✗ Too large	—

What to watch out for

Q2_K is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
4 larger variants of Devstral do not fit and would need CPU offload or different hardware.
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 mini M4 16 GB limitations

The cheapest credible always-on local-AI box, but 16 GB caps it at small and mid-size models.
Memory is soldered; upgrading means replacing the machine.

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.
16 GB unified memory at 120 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