Check my GPU

on

Can the Apple M5 Max (64 GB) run Gemma 4 12B?

83 ptsGreat (A) · 83 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.2/15

Yes, it runs well

Runs well. At Q6_K it needs about 14.9 GB of 48.0 GB usable, with an estimated speed of 37.7 tok/s.

Best quant
Q6_K
Generation speed
37.7 tok/s
Prompt processing
980 tok/s
First token (1K prompt)
1.0 s
Largest safe context
256K

Download Gemma 4 12B

Recommended for the Apple M5 Max (64 GB): Q6_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 gemma4:12b

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 Q6_K 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:Q6_K

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 7 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.37.0 / 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.14.6 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.7.2 / 15
Total83.7 / 10083 ptsGreat (A) · 83 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.2/15

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

Every quantization on the Apple M5 Max (64 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 9.9 GB 48.0 GB 89.1 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 GGUF (UD-Q2_K_XL) (opens in a new tab)
Q3_K_M 11.0 GB 48.0 GB 70.2 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 31.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15 GGUF (opens in a new tab)
Q4_K_M 12.4 GB 48.0 GB 54.3 tok/s Runs well 81 ptsGreat (A) · 81 of 100 points: Model quality 35.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 GGUF (opens in a new tab)
Q5_K_M 13.6 GB 48.0 GB 44.8 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.5/15 GGUF (opens in a new tab)
Q6_K 14.9 GB 48.0 GB 37.7 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.2/15 GGUF (opens in a new tab)
Q8_0 17.8 GB 48.0 GB 27.6 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 8.6/15 GGUF (opens in a new tab)
F16 29.0 GB 48.0 GB 12.7 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 8.5/15, Memory use 14.0/15 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

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.