Can the Apple M3 Pro (18 GB) run Gemma 4 12B?

84 pts

Yes, it runs well

Runs well. At Q4_K_M it needs about 9.5 GB of 12.1 GB usable, with an estimated speed of 13.3 tok/s.

Best quant: Q4_K_M
Generation speed: 13.3 tok/s
Prompt processing: 384 tok/s
First token (1K prompt): 2.7 s
Largest safe context: 38K

Download Gemma 4 12B

Recommended for the Apple M3 Pro (18 GB): Q4_K_M. 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 gemma4:12b-it-q4_K_M

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 Q4_K_M file (opens in a new tab)

huggingface.co/unsloth/gemma-4-12B-it-GGUF (opens in a new tab)

ollama run hf.co/unsloth/gemma-4-12B-it-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/google/gemma-4-12B-it (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/google-deepmind/gemma (opens in a new tab)

git clone https://github.com/google-deepmind/gemma

Google DeepMind’s official Gemma library.

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

How the A 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.	35.5 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	8.6 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Total	84.1 / 100	84 ptsGreat (A) · 84 of 100 points: Model quality 35.5/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 15.0/15

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

Every quantization on the Apple M3 Pro (18 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	7.0 GB	12.1 GB	21.8 tok/s	Runs well	75 ptsGreat (A) · 75 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 13.4/15	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	8.1 GB	12.1 GB	17.1 tok/s	Runs well	81 ptsGreat (A) · 81 of 100 points: Model quality 31.4/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q4_K_M`	9.5 GB	12.1 GB	13.3 tok/s	Runs well	84 ptsGreat (A) · 84 of 100 points: Model quality 35.5/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q5_K_M`	10.7 GB	12.1 GB	11.0 tok/s	Tight fit	83 ptsGreat (A) · 83 of 100 points: Model quality 36.2/45, Memory fit 24.0/25, Speed 7.8/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q6_K`	12.0 GB	12.1 GB	9.2 tok/s	Tight fit	83 ptsGreat (A) · 83 of 100 points: Model quality 37.0/45, Memory fit 24.0/25, Speed 7.2/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q8_0`	14.9 GB	12.1 GB	5.7 tok/s	Heavy offload	62 ptsGood (B) · 62 of 100 points: Model quality 37.4/45, Memory fit 4.0/25, Speed 5.7/15, Memory use 15.0/15	GGUF (opens in a new tab)
`F16`	26.2 GB	12.1 GB	—	Won't run	11 ptsWon't run (F) · 11 of 100 points: Model quality 11.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

92 ptsExcellent (S) · 92 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 F16 · 43.2 tok/s
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q6_K · 47.9 tok/s
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q6_K · 52.4 tok/s
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q6_K · 63.8 tok/s
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 Q6_K · 68.4 tok/s
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15 AMD Radeon RX 7900 XTX Q8_0 · 43.2 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.