What you need to run Gemma 4 12B

About Gemma 4 12B

Gemma 4 12B is a general chat model from Google. Sweet spot for 16 GB machines. Good writing and reasoning. Running it locally needs about 8.9 GB of memory, and the download is 8 GB.

Smallest Mac that runs it

The least memory you need, by Apple chip:

• M1: does not fit
• M1 Pro: from 16 GB
• M1 Max: from 32 GB
• M1 Ultra: from 64 GB
• M2: from 16 GB
• M2 Pro: from 16 GB
• M2 Max: from 32 GB
• M2 Ultra: from 64 GB
• M3: from 16 GB
• M3 Pro: from 18 GB
• M3 Max: from 36 GB
• M3 Ultra: from 96 GB
• M4: from 16 GB
• M4 Pro: from 24 GB
• M4 Max: from 36 GB
• M5: from 16 GB
• M5 Pro: from 24 GB
• M5 Max: from 36 GB

Graphics cards

Runs well on: RTX 3060 12GB, RTX 3080 10GB, RTX 3090, RTX 4060 Ti 16GB, RTX 4070 / 4070 Super, RTX 4070 Ti Super, RTX 4080 / 4080 Super, RTX 4090, RTX 5060 Ti 16GB, RTX 5070, RTX 5070 Ti, RTX 5080, RTX 5090, Radeon RX 7800 XT, Radeon RX 9070 XT, Radeon RX 7900 XTX. Runs slowly with help from system RAM on: RTX 3070, RTX 4060, RTX 5060.

Hardware to run it

As an Amazon Associate I earn from qualifying purchases.

• Smallest Mac: M5 with 16 GB. See it on Amazon
• Smallest graphics card: RTX 3080 10GB (10 GB). See it on Amazon
• Storage: this model is a 8 GB download, and most people end up keeping several. A fast external SSD keeps your main drive free. See SSDs on Amazon

Lighter and heavier alternatives

• Gemma 4 E4B: needs about 7.4 GB, a lighter choice. Best small model for everyday questions and writing.
• Qwen 3.5 9B: needs about 7.4 GB, a lighter choice. Strong everyday helper, 256K context, sees images.
• gpt-oss 20B: needs about 15.2 GB, a heavier choice. OpenAI's open model. Smart for its size and fast because only part of it runs per word.
• Gemma 4 26B A4B: needs about 19.4 GB, a heavier choice. Mixture of experts: big-model quality at small-model speed.

Questions