Model family · 7 sizes

Gemma: which size runs locally?

Gemma comes in 7 sizes, from 1B to 27B. Bigger is generally more capable but needs more memory. Here is each size with its Q4_K_M weight, the memory it needs, and the hardware that runs it.

Sizes: 7
Smallest: 1B
Largest: 27B
Runs from: 8GB

The Gemma lineup

Smallest first Q4_K_M · min memory

"Needs" is the sourced minimum memory for Q4_K_M with a small context. Larger context needs more.

Which Gemma fits your memory

8GB

Largest that fits: Gemma 3 4B (4B), best case on Apple M1 (8GB).

Yes

16GB

Largest that fits: Gemma 3 12B (12B), best case on Nvidia GeForce RTX 4080 (16GB).

Yes

24GB

Largest that fits: Gemma 3 27B (27B), best case on Nvidia GeForce RTX 4090 (24GB).

Yes

32GB

Largest that fits: Gemma 3 27B (27B), best case on Nvidia GeForce RTX 5090 (32GB).

Yes

Best case means the most capable device at that size (usually a discrete GPU). A Mac at the same size sits roughly one rung lower; see the per-size breakdown on each memory budget page.

FAQ

Which Gemma size should I run locally?

Pick the largest size your memory allows. On 8GB (best case) up to Gemma 3 4B; On 16GB (best case) up to Gemma 3 12B; On 24GB (best case) up to Gemma 3 27B; On 32GB (best case) up to Gemma 3 27B. Smaller sizes run faster and leave headroom for context.

What is the smallest Gemma model?

Gemma 3 1B at 1B parameters, about 0.81 GB on disk at Q4_K_M and roughly 2 GB of memory to run. It is the one to use on phones and 8 GB machines.

What is the largest Gemma model and what does it need?

Gemma 3 27B at 27B, about 16.55 GB at Q4_K_M and roughly 20 GB of memory. It fits a high-memory desktop GPU or Mac.

Sources

Memory figures are estimates at Q4_K_M. See methodology.