Rent a GPU

Can the Apple M4 Pro (24GB) run Gemma 4 26B-A4B?

Apple M4 Pro (24GB) × Gemma 4 26B-A4B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M13.5 GB of 16.1 GB
Weights 12.6 GBKV cache 0.3 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Speed~88tokens per second
Max context253Ktokens that fit at Q3_K_M
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Only just. Gemma 4 26B-A4B fits on the Apple M4 Pro (24GB) at Q3_K_M, which costs noticeable quality. Expect about 88 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default gemma4:26b download is Q4_K_M, which needs about 16.5 GB, more than the 16.1 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the Apple M4 Pro (24GB)

Run it in the cloud

Want full quality? Run Gemma 4 26B-A4B on a bigger rented GPU.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

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 16.1 GB the Apple M4 Pro (24GB) can use. macOS lets the GPU use about 16.1 GB of the 24 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality52.5 GBToo big—
Q8_0Near-lossless28.3 GBToo big—
Q6_KExcellent22 GBToo big—
Q5_K_MVery good19.2 GBToo big—
Q4_K_MGood, most popular16.5 GBToo big—
Q3_K_MNoticeably degraded13.5 GBFits~88 tok/s
Q2_KHeavily degraded10.6 GBFits~115 tok/s

Measured speed from real Apple M4 Pro (24GB) owners

Tokens per second that people measured on their own Apple M4 Pro (24GB), next to our estimate.

No one has measured Gemma 4 26B-A4B on the Apple M4 Pro (24GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M4 Pro (24GB)? 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

Check Radeon RX 7900 XT prices

Models that run well on the Apple M4 Pro (24GB)

Frequently asked questions

Can Apple M4 Pro (24GB) run Gemma 4 26B-A4B?

Only just. Gemma 4 26B-A4B fits on the Apple M4 Pro (24GB) at Q3_K_M, which costs noticeable quality. Expect about 88 tokens/second. A card with more memory is a better experience.

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 M4 Pro (24GB)?

Roughly 88 tokens per second at Q3_K_M, estimated from the Apple M4 Pro (24GB)'s 273 GB/s memory bandwidth.