Check my GPU

on

Can the Apple M2 Pro (32 GB) run Gemma 4 26B-A4B?

91 ptsExcellent (S) · 91 of 100 points: Model quality 39.5/45, Memory fit 24.0/25, Speed 12.5/15, Memory use 15.0/15

Yes, with little memory to spare

Tight fit. At Q4_K_M it needs about 18.5 GB of 21.4 GB usable, with an estimated speed of 27.8 tok/s.

Best quant
Q4_K_M
Generation speed
27.8 tok/s
Prompt processing
1,109 tok/s
First token (1K prompt)
0.9 s
Largest safe context
67K

Download Gemma 4 26B-A4B

Recommended for the Apple M2 Pro (32 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 gemma4:26b-a4b-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-4-26B-A4B-it-GGUF (opens in a new tab)

ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/google/gemma-4-26B-A4B-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 6 days ago against Hugging Face, Ollama and GitHub.

How the S 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.39.5 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.12.5 / 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
Total91.1 / 10091 ptsExcellent (S) · 91 of 100 points: Model quality 39.5/45, Memory fit 24.0/25, Speed 12.5/15, 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 M2 Pro (32 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 13.0 GB 21.4 GB 45.7 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15 GGUF (UD-Q2_K_XL) (opens in a new tab)
Q3_K_M 15.4 GB 21.4 GB 36.0 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 35.0/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q4_K_M 18.5 GB 21.4 GB 27.8 tok/s Tight fit 91 ptsExcellent (S) · 91 of 100 points: Model quality 39.5/45, Memory fit 24.0/25, Speed 12.5/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q5_K_M 21.0 GB 21.4 GB 23.0 tok/s Tight fit 90 ptsExcellent (S) · 90 of 100 points: Model quality 40.4/45, Memory fit 24.0/25, Speed 11.4/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 23.9 GB 21.4 GB 16.4 tok/s Heavy offload 69 ptsGood (B) · 69 of 100 points: Model quality 41.2/45, Memory fit 4.0/25, Speed 9.6/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 30.1 GB 21.4 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF (opens in a new tab)
F16 54.3 GB 21.4 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (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.