Can Phi 3 Medium 14B run on MacBook Air M4 24GB?

YES — Tight Fit

B58Good

▲Estimated — low-sample bucket· few comparable runs

Phi 3 Medium 14B needs ~15.1 GB VRAM. MacBook Air M4 24GB has 17.3 GB. With Q4_K_M quantization, expect ~10 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: 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) — 15.1 GB, 9.6 tok/s, Tight fit

15.1 GB required17.3 GB available

87% VRAM used

Fit status

Tight fit

Decode

9.6 tok/s

TTFT

20228 ms

Safe context

28K

Memory

15.1 GB / 17.3 GB

Memory breakdown

Weights8.5 GB

KV Cache3.1 GB

Runtime0.9 GB

Headroom2.6 GB

See how fast it feels

See how fast it feelsPhi 3 Medium 14B on MacBook Air M4 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: 9.6 tok/s decode · 20.2s TTFT (warm) · 24 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	9.6 tok/s	11034 ms	28K
Coding	B	Tight fit	9.6 tok/s	20228 ms	28K
Agentic Coding	B	Runs with offload (needs ~0.4 GB host RAM)	8.7 tok/s	32223 ms	28K
Reasoning	B	Tight fit	9.6 tok/s	23906 ms	28K
RAG	B	Runs with offload (needs ~0.4 GB host RAM)	8.7 tok/s	40278 ms	28K

Quantization options

How Phi 3 Medium 14B (14B params) fits at each quantization level on MacBook Air M4 24GB (17.3 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	B60
Q3_K_S	3	6.9 GB	Low	B61
NVFP4	4	7.8 GB	Medium	B62
Q4_K_M	4	8.5 GB	Medium	B62
Q5_K_M	5	10.1 GB	High	B62
Q6_KBest for your GPU	6	11.5 GB	High	B62
Q8_0	8	15.0 GB	Very High	F0
F16	16	28.7 GB	Maximum	F0