Gemma Models: Google's Lightweight Local AI

Google DeepMind's Gemma family delivers impressive quality from compact models. The current Gemma 4 line starts with E4B, a 4.5B on-device model that runs on an 8GB Mac, then steps up to the 26B-A4B MoE (25.2B total, 3.8B active, 16GB load) and the dense 31B (20GB load, 32GB floor) — all Apache 2.0, with the 31B taking text and images. If you want a well-tuned, safety-conscious model that fits modest hardware, Gemma is a strong choice.

Google DeepMind19 local models

DEVELOPER

Google DeepMind

MODELS

SIZE RANGE

1B–31B

RAM RANGE

2–48 GB

Bar chart: maximum local LLM size by memory tier. 8 GB runs up to 9B, 12 GB runs up to 12B, 16 GB runs up to 14B, 24 GB runs up to 27B, 32 GB runs up to 35B, 36 GB runs up to 35B, 48 GB runs up to 35B, 64 GB runs up to 70B, 72 GB runs up to 70B, 96 GB runs up to 70B, 128 GB runs up to 70B, 192 GB runs up to 70B, 256 GB runs up to 70B, 512 GB runs up to 405B. Data from ModelFit's own catalog.

Key Features

Gemma 4 E4B: 4.5B effective, runs on 8GB Macs

Gemma 4 26B-A4B MoE: 25.2B total, 3.8B active

Gemma 4 31B dense: 20GB load, 32GB RAM floor

Apache 2.0 across the Gemma 4 line

Previous Gemma 2 / 3 sizes still on Ollama

All Gemma Models

Model	Size	Quant	VRAM	Min RAM	Best For	Quality
Gemma 3 1B Instruct	1B	Q4_K_M	1 GB	2 GB	Chat, Mobile	52
Gemma 3 1B Instruct (Q8)	1B	Q8_0	1 GB	4 GB	Chat, Mobile	54
Gemma 2 2B Instruct	2B	Q4_K_M	1.8 GB	4 GB	Chat	58
Gemma 4 E2B	2.3B	Q4_K_M	2.3 GB	4 GB	IoT, Mobile, Edge	68
Gemma 4 E2B (Q8)	2.3B	Q8_0	4.6 GB	8 GB	IoT, Mobile, Edge	70
Gemma 3 4B Instruct	4B	Q4_K_M	3.5 GB	6 GB	Chat, Coding	72
Gemma 3 4B Instruct (Q8)	4B	Q8_0	3.9 GB	8 GB	Chat, Coding	74
Gemma 4 E4B	4.5B	Q4_K_M	4 GB	6 GB	On-device, Mobile, Chat	78
Gemma 4 E4B (Q8)	4.5B	Q8_0	7.5 GB	16 GB	On-device, Mobile, Chat	80
Gemma 2 9B Instruct	9B	Q4_K_M	7 GB	12 GB	Chat, Coding	76
Gemma 3 12B Instruct	12B	Q4_K_M	9.5 GB	16 GB	Chat, Quality	85
Gemma 4 12B	12B	Q4_K_M	8 GB	12 GB	Chat, Coding, Multimodal	90
Gemma 4 12B (Q8)	12B	Q8_0	12.8 GB	24 GB	Chat, Coding, Multimodal	92
Gemma 4 26B-A4B	26B	Q4_K_M	16 GB	24 GB	Chat, Coding, Multimodal	91
Gemma 4 26B-A4B (Q8)	26B	Q8_0	28.1 GB	48 GB	Chat, Coding, Multimodal	93
Gemma 2 27B Instruct	27B	Q4_K_M	21 GB	32 GB	Quality, Coding	80
Gemma 3 27B Instruct	27B	Q4_K_M	21 GB	32 GB	Quality, Coding	89
Gemma 4 31B	31B	Q4_K_M	20 GB	32 GB	Quality, Coding, Multimodal	93
Gemma 4 31B (Q8)	31B	Q8_0	30.9 GB	48 GB	Quality, Coding, Multimodal	95

Device Compatibility

Which Gemma models can run on each device class, based on minimum RAM requirements.

Model	iPhone	Air	Pro	Studio	Mini
Gemma 3 1B Instruct (1B)	Excellent	Excellent	Excellent	Excellent	Excellent
Gemma 3 1B Instruct (Q8) (1B)	Excellent	Excellent	Excellent	Excellent	Excellent
Gemma 2 2B Instruct (2B)	Excellent	Excellent	Excellent	Excellent	Excellent
Gemma 4 E2B (2.3B)	Excellent	Excellent	Excellent	Excellent	Excellent
Gemma 4 E2B (Q8) (2.3B)	Possible	Possible	Excellent	Excellent	Excellent
Gemma 3 4B Instruct (4B)	Possible	Possible	Excellent	Excellent	Excellent
Gemma 3 4B Instruct (Q8) (4B)	Possible	Possible	Excellent	Excellent	Excellent
Gemma 4 E4B (4.5B)	Possible	Possible	Excellent	Excellent	Excellent
Gemma 4 E4B (Q8) (4.5B)	No	Possible	Possible	Excellent	Possible
Gemma 2 9B Instruct (9B)	Possible	Possible	Possible	Excellent	Possible
Gemma 3 12B Instruct (12B)	No	Possible	Possible	Excellent	Possible
Gemma 4 12B (12B)	Possible	Possible	Possible	Excellent	Possible
Gemma 4 12B (Q8) (12B)	No	Possible	Possible	Possible	Possible
Gemma 4 26B-A4B (26B)	No	Possible	Possible	Possible	Possible
Gemma 4 26B-A4B (Q8) (26B)	No	No	Possible	Possible	Possible
Gemma 2 27B Instruct (27B)	No	Possible	Possible	Possible	Possible
Gemma 3 27B Instruct (27B)	No	Possible	Possible	Possible	Possible
Gemma 4 31B (31B)	No	Possible	Possible	Possible	Possible
Gemma 4 31B (Q8) (31B)	No	No	Possible	Possible	Possible

RAM Requirements

Gemma 3 1B Instruct

1 GB · min 2 GB

Gemma 3 1B Instruct (Q8)

1 GB · min 4 GB

Gemma 2 2B Instruct

1.8 GB · min 4 GB

Gemma 4 E2B

2.3 GB · min 4 GB

Gemma 4 E2B (Q8)

4.6 GB · min 8 GB

Gemma 3 4B Instruct

3.5 GB · min 6 GB

Gemma 3 4B Instruct (Q8)

3.9 GB · min 8 GB

Gemma 4 E4B

4 GB · min 6 GB

Gemma 4 E4B (Q8)

7.5 GB · min 16 GB

Gemma 2 9B Instruct

7 GB · min 12 GB

Gemma 3 12B Instruct

9.5 GB · min 16 GB

Gemma 4 12B

8 GB · min 12 GB

Gemma 4 12B (Q8)

12.8 GB · min 24 GB

Gemma 4 26B-A4B

16 GB · min 24 GB

Gemma 4 26B-A4B (Q8)

28.1 GB · min 48 GB

Gemma 2 27B Instruct

21 GB · min 32 GB

Gemma 3 27B Instruct

21 GB · min 32 GB

Gemma 4 31B

20 GB · min 32 GB

Gemma 4 31B (Q8)

30.9 GB · min 48 GB

Frequently Asked Questions

What is the best Gemma model for a MacBook Air?

Gemma 4 E4B is the current pick for an 8GB Air: `ollama run gemma4:e4b` needs 6GB RAM minimum and loads about 4GB. On a 16GB machine you can move up to the larger Gemma 3 or Gemma 2 sizes, and 24GB+ opens the Gemma 4 26B-A4B MoE.

Can Gemma run on an iPhone?

Yes. Gemma 4 E4B is built for on-device use and runs on high-end iPhones and any 8GB Mac. Quality is basic but useful for simple chat and text tasks.

How does Gemma compare to Llama at similar sizes?

At small sizes they are close. Gemma tends to be more conservative and safety-tuned, while Llama is more flexible and has a larger fine-tune ecosystem. Pick based on whether you want guardrails or freedom.

Related Model Families

PhiMicrosoft

LlamaMeta

QwenAlibaba Cloud

Getting Started

How to Set Up Ollama Best LLM for iPhone Browse All Devices ModelFit Wizard