Can the Apple M2 (8 GB) run Phi-3 Medium (14B)?

4 pts

No, it doesn’t fit

No. Phi-3 Medium (14B) needs about 7.5 GB even at Q2_K; the Apple M2 (8 GB) has 5.4 GB usable.

Download Phi-3 Medium (14B)

Recommended: Q2_K. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run phi3:14b-medium-4k-instruct-q2_K

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q2_K file (opens in a new tab)

huggingface.co/bartowski/Phi-3-medium-4k-instruct-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Phi-3-medium-4k-instruct-GGUF:Q2_K

Original weights · Hugging Face

Full-precision files from Microsoft, for fine-tuning, vLLM, Transformers.

huggingface.co/microsoft/Phi-3-medium-4k-instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Microsoft. The weights themselves download from Hugging Face.

github.com/microsoft/PhiCookBook (opens in a new tab)

git clone https://github.com/microsoft/PhiCookBook

Microsoft’s official Phi cookbook: setup, inference and fine-tuning guides.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

How the F grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	4.3 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Total	4.3 / 100	4 ptsWon't run (F) · 4 of 100 points: Model quality 4.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the Apple M2 (8 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	7.5 GB	5.4 GB	—	Won't run	4 ptsWon't run (F) · 4 of 100 points: Model quality 4.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q3_K_M`	8.7 GB	5.4 GB	—	Won't run	5 ptsWon't run (F) · 5 of 100 points: Model quality 5.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q4_K_M`	10.4 GB	5.4 GB	—	Won't run	5 ptsWon't run (F) · 5 of 100 points: Model quality 5.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q5_K_M`	11.8 GB	5.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q6_K`	13.3 GB	5.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q8_0`	16.7 GB	5.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`F16`	29.8 GB	5.4 GB	—	Won't run	6 ptsWon't run (F) · 6 of 100 points: Model quality 6.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Hardware that can run it

75 ptsGreat (A) · 75 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q8_0 · 41.9 tok/s
75 ptsGreat (A) · 75 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q8_0 · 45.1 tok/s
75 ptsGreat (A) · 75 of 100 points: Model quality 20.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q5_K_M · 40.0 tok/s
75 ptsGreat (A) · 75 of 100 points: Model quality 20.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q5_K_M · 48.8 tok/s
75 ptsGreat (A) · 75 of 100 points: Model quality 20.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q5_K_M · 53.5 tok/s
75 ptsGreat (A) · 75 of 100 points: Model quality 20.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q5_K_M · 65.1 tok/s

Models that do run on the Apple M2 (8 GB)

77 ptsGreat (A) · 77 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 11.9/15, Memory use 15.0/15 TMax 4B Q4_K_M · 25.1 tok/s
77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 15.0/15 Qwen3.5 4B Q4_K_M · 22.7 tok/s
77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 15.0/15 Gemma 4 E2B Q4_K_M · 20.6 tok/s
77 ptsGreat (A) · 77 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 11.4/15, Memory use 15.0/15 Agents-A1 4B Q4_K_M · 23.3 tok/s
76 ptsGreat (A) · 76 of 100 points: Model quality 22.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Ling 3.0 Tiny (8B-A1.3B) Q3_K_M · 52.6 tok/s

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.