Yes, just — 0.3 GB spare

Phi-4 14B at Q4_K_M fits your M4 · 16 GB entirely in unified memory at 8K context, at an estimated 8.1 tokens per second. Past 9K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully in unified memory 8K context Q4_K_M · 8.3 GB MIT Released Dec 2024

Trained heavily on synthetic reasoning data. Short 16K window is its main limitation.

Hardware requirements What hardware do I need to run Phi-4 14B? →

At Q4_K_M with an 8K context: a 16 GB GPU (RTX 5080) or a 24 GB Mac (M4 Pro). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 8.3 GB
Weights 8.3 GB KV cache @ 8K 1.56 GB Runtime overhead 0.6 GB Free 0.3 GB of 10.7 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 27.4 GB 29.5 GB — ~2.4 Reference 18.8 GB over
Q8_0 14.5 GB 16.7 GB — ~4.6 −0.1% ppl 6.0 GB over
Q6_K 11.2 GB 13.4 GB — ~6.0 −0.4% ppl 2.7 GB over
Q5_K_M 9.7 GB 11.9 GB 2K ~6.9 −0.8% ppl 1.2 GB over
Q4_K_M 8.3 GB 10.4 GB 9K 8.1 −1.9% ppl Recommended
Q3_K_M 6.7 GB 8.9 GB 16K 10 −5.4% ppl Fits
Q2_K 5.7 GB 7.9 GB 16K 12 −15% ppl Fits

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/phi-4-4bit \
    --max-tokens 512 --prompt "Hello"

Apple's own array framework. The fastest path on Apple Silicon. More on MLX.

01Download is 8.3 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 10.7 GB of 16 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03Only 0.3 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 9K context.
See all models for this rig Compare with another model

Related models on an M4 · 16 GB

ModelTotalTok/s est.
Phi-4-mini 3.8B
3.84B · same family
Q4_K_M · 3.8 GB 31 Runs great
Qwen3 14B
14.8B · similar size
Q4_K_M · 10.2 GB 8.1 Tight fit
DeepSeek-R1-Distill-Qwen 14B
14.8B · similar size
Q4_K_M · 10.4 GB 8.1 Tight fit
Qwen2.5-Coder 14B
14.8B · similar size
Q4_K_M · 10.4 GB 8.1 Tight fit
Ministral 3 14B
13.9B · similar size
Q4_K_M · 9.7 GB 8.6 Tight fit
Gemma 3 12B
12.2B · similar size
Q4_K_M · 8.3 GB 9.8 Runs great
Mistral NeMo 12B
12.2B · similar size
Q4_K_M · 8.7 GB 9.8 Runs great

Every model against the M4 · 16 GB →

Phi-4 14B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
10.4 GB ~8.0 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
10.4 GB 26 Tight fit
GeForce RTX 5080
14.4 GB usable · 960 GB/s
10.4 GB 70 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
10.4 GB 74 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
10.4 GB 70 Runs great
M4 Pro · 24 GB
18.0 GB usable · 273 GB/s
10.4 GB 18 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
10.4 GB 27 Runs great

All 114 devices, by tier →