Can you run Gemma 4 26B-A4B-it on Apple M1?
Short answer
Gemma 4 26B-A4B-it will run on the CPU alone, and whether that is usable depends on the model.
- Model file
- 15.8 GB
- Needs in VRAM, with context
- about 16.9 GB
- Memory
- system RAM, shared
- Measured on this hardware
- not measured
How this was worked out
Gemma 4 26B-A4B-it is a 15.8 GB file. Running it needs the weights in memory plus room for the context window and the runtime, which comes to roughly 16.9 GB in practice. Apple M1 has no dedicated video memory, so the model runs in system RAM on the CPU. That is arithmetic rather than a benchmark: it tells you whether the model loads, not how it feels.
What we have actually measured
We have not timed Gemma 4 26B-A4B-it on Apple M1. The closest figure we have is no measurement of this model at all yet. Rather than scale that number to your card and present the result as a benchmark, this page leaves it out. The method is published at /benchmarks if you would like to run it yourself.
If it is tight
There is no card to run out of, so the limit is patience rather than memory. Small models are fine here; the large ones are not. Nightjar sizes the context window to the memory it finds, so a smaller card gets a shorter window rather than a failed load.
Smaller models that fit the same card
- Qwen 3.5 9B on Apple M1 — 5.3 GB
- Gemma 4 12B-it on Apple M1 — 6.6 GB
- Qwen 3.5 27B on Apple M1 — 15.6 GB
Related
- Up a levelCan your PC run a local AI model?
- Closely relatedCan you run Gemma 4 12B-it on Apple M1?
- Closely relatedCan you run Gemma 4 26B-A4B-it on Intel Arc A770?
- Closely relatedCan you run Gemma 4 26B-A4B-it on Intel Arc B580?
- Closely relatedCan you run Gemma 4 26B-A4B-it on CPU only?
- Elsewhere on the siteLocal AI on Apple M1: which models run and how fast
- Elsewhere on the siteGemma 4 26B-A4B-it in Nightjar: speed, size and what it is good at