Rent a GPU

Can the Apple M3 Pro (36GB) run Gemma 4 26B-A4B?

Apple M3 Pro (36GB) × Gemma 4 26B-A4B8K context
YesRuns fully on the GPU
Memory at Q6_K22 GB of 24.1 GB
Weights 21.2 GBKV cache 0.3 GBRuntime 0.6 GB
QuantQ6_KExcellent
Speed~29tokens per second
Max context205Ktokens that fit at Q6_K
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The Apple M3 Pro (36GB) can run Gemma 4 26B-A4B fully in unified memory at Q6_K (excellent), using about 22 GB of the 24.1 GB available, at roughly 29 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 4 26B-A4B:

ollama run gemma4:26b

Ollama's default download is Q4_K_M (about 16.5 GB here). You have room for Q6_K, which is excellent: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M3 Pro (36GB)

Run it in the cloud

No Apple M3 Pro (36GB)? Run Gemma 4 26B-A4B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 24.1 GB the Apple M3 Pro (36GB) can use. macOS lets the GPU use about 24.1 GB of the 36 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality52.5 GBToo big—
Q8_0Near-lossless28.3 GBToo big—
Q6_KExcellent22 GBFits~29 tok/s
Q5_K_MVery good19.2 GBFits~33 tok/s
Q4_K_MGood, most popular16.5 GBFits~39 tok/s
Q3_K_MNoticeably degraded13.5 GBFits~48 tok/s
Q2_KHeavily degraded10.6 GBFits~63 tok/s

Measured speed from real Apple M3 Pro (36GB) owners

Tokens per second that people measured on their own Apple M3 Pro (36GB), next to our estimate.

No one has measured Gemma 4 26B-A4B on the Apple M3 Pro (36GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M3 Pro (36GB)? Add your real speed

One command times Gemma 4 26B-A4B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- gemma4:26b

Windows (PowerShell)

$env:GPUFIT_MODEL="gemma4:26b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Gemma 4 26B-A4B comfortably

Models that run well on the Apple M3 Pro (36GB)

Frequently asked questions

Can Apple M3 Pro (36GB) run Gemma 4 26B-A4B?

Yes. The Apple M3 Pro (36GB) can run Gemma 4 26B-A4B fully in unified memory at Q6_K (excellent), using about 22 GB of the 24.1 GB available, at roughly 29 tokens/second.

How much VRAM does Gemma 4 26B-A4B need?

About 16.5 GB at Q4_K_M with 8,192 tokens of context, and about 52.5 GB at full FP16 precision.

How fast is Gemma 4 26B-A4B on the Apple M3 Pro (36GB)?

Roughly 29 tokens per second at Q6_K, estimated from the Apple M3 Pro (36GB)'s 150 GB/s memory bandwidth.