Can I Run LFM2.5 on Mac mini (M4, 16 GB)?

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026

Yes

Yes — LFM2.5-8B-A1B at Q8_0 needs about 10.8 GB of the 12 GB usable on Mac mini (M4, 16 GB) (~1.2 GB spare), at ~27.7 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~27.7 tok/s

Buy This HardwareIntel Arc B580 12GB — 12 GB VRAM · 190 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)

LFM2.5 on Mac mini (M4, 16 GB): memory by quantization

Quant	Memory needed	Fits 12 GB?	Max context	Est. speed	Download
F16	18.6 GB	✗ No	—	—	16.6 GB
Q8_0	10.8 GB	✓ Yes	16K	~27.7 tok/s	8.8 GB
Q6_K	8.8 GB	✓ Yes	16K	~32.6 tok/s	6.8 GB
Q5_K_M	7.9 GB	✓ Yes	32K	~35.6 tok/s	5.9 GB
Q4_K_M	7 GB	✓ Yes	32K	~38.9 tok/s	5 GB
Q3_K_M	5.5 GB	✓ Yes	32K	~46.2 tok/s	3.5 GB
Q2_K	4.7 GB	✓ Yes	32K	~51.5 tok/s	2.7 GB

What to watch out for

Only ~1.2 GB of headroom at Q8_0: a longer context or a second application can push this into swapping.
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 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 inferred from the parameter count because this model does not publish its full attention configuration.

FAQ