Can Phi 4 Mini 4B run on Mac mini M2 24GB?

YES — Runs Great

B68Good

○Estimated from fit model

Phi 4 Mini 4B needs ~7.4 GB VRAM. Mac mini M2 24GB has 17.3 GB. With Q4_K_M quantization, expect ~27 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: Very lowStack: StandardBottleneck: Memory bandwidth

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 7.4 GB, 28.6 tok/s, Runs well

7.4 GB required17.3 GB available

43% VRAM used

Fit status

Runs well

Decode

28.6 tok/s

TTFT

6760 ms

Safe context

124K

Memory

7.4 GB / 17.3 GB

Memory breakdown

Weights2.4 GB

KV Cache1.5 GB

Runtime0.9 GB

Headroom2.6 GB

See how fast it feels

See how fast it feelsPhi 4 Mini 4B on Mac mini M2 24GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
 - Speed = 60 mph (miles per hour)
 - Time = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
 Distance = 60 mph x 2.5 h
 = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
 - First half: 1.25 hours at 60 mph = 75 miles
 - Stop: 20 minutes (no distance)
 - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 28.6 tok/s decode · 6.8s TTFT (warm) · 72 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	26.6 tok/s	3964 ms	124K
Coding	B	Runs well	26.6 tok/s	7267 ms	124K
Agentic Coding	B	Runs well	26.6 tok/s	10571 ms	124K
Reasoning	B	Runs well	26.6 tok/s	8589 ms	124K
RAG	B	Runs well	26.6 tok/s	13214 ms	124K