Skip to content
Local AI Wizard
Your machine
Theme

Gemma 4 family: which size to run

5 sizes, 5.1B–30.7B parameters · Google

Checked

Sizes

Gemma 4 sizes
ModelArchitecture
Gemma 4 E2BGoogle · Apache 2.0 · Mar 31, 20265.1BDense131,072No LiveBench result for this model in release 2026-06-2512*6*3.14.3
Gemma 4 E4BGoogle · Apache 2.0 · Mar 31, 20268BDense131,072No LiveBench result for this model in release 2026-06-2514*8*56.8
Gemma 4 12BGoogle · Apache 2.0 · Jun 3, 202611.95BDense262,144No LiveBench result for this model in release 2026-06-2517117.16.7
Gemma 4 26B A4BGoogle · Apache 2.0 · Mar 31, 202625.2BMoE · 3.8B active262,144No LiveBench result for this model in release 2026-06-25272116.9†15.6
Gemma 4 31BGoogle · Apache 2.0 · Mar 31, 202630.7BDense262,144No LiveBench result for this model in release 2026-06-25322618.318.4

Each size is its own model, with its own scores and memory needs. Q4 estimates are planning figures, not measurements; file sizes are published. The Mac or PC column is for a 32 GB or larger machine (8 GB reserve); machines under 32 GB reserve 25% of their memory (2 to 8 GB), so they need less. The publisher lists E2B, E4B, 12B, 26B A4B, 31B. * The model's page explains why its estimate differs.

† Unsloth's dynamic UD-Q4_K_M file, shown when the repository has no plain Q4_K_M file (the same rule as the model pages); the cell's title names the file.

How to read this table

Q4 means compressed to about 4 bits per weight. GGUF (llama.cpp, Ollama, LM Studio) and MLX (Apple silicon) are file formats; the sizes shown are the published 4-bit files. A dash means no value is published or collected for that size; the reason is in the cell's accessible text.

Which size fits my machine

The largest size whose Q4 planning estimate fits what each machine offers. A planning estimate, not a measurement and not a speed.

Largest Gemma 4 size per machine
MachineLargest Gemma 4 size with enough memory
Mac mini M2 · 8 GB unified8Gemma 4 E4B8
Mac mini M4 · 16 GB unified16Gemma 4 12B13
Mac mini M4 · 24 GB unified24Gemma 4 12B15
Mac mini M4 · 32 GB unified32Gemma 4 31B32
Mac mini M5 Pro · 64 GB unified56Gemma 4 31B32
Mac Studio M5 Max · 128 GB unified104Gemma 4 31B32
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unified392Gemma 4 31B32
RTX 4060 · 8 GB VRAM8Gemma 4 E4B8
RTX 3060 · 12 GB VRAM12Gemma 4 12B11
RTX 5080 · 16 GB VRAM16Gemma 4 12B11
RTX 4090 · 24 GB VRAM24Gemma 4 26B A4B21
RTX 5090 · 32 GB VRAM32Gemma 4 31B26
DGX H100 · 8 × 80 GB640Gemma 4 31B40

A dash means no size of this family fits that machine. The requirement is the size's Q4 estimate with that machine's own reserve: a graphics card reserves 2 GB, as in the sizes table; a Mac or PC reserves 25% of its memory (2 to 8 GB), so below 32 GB its figure is lower than the sizes table's. A server profile reserves 2 GB per graphics card, so its figure is higher.

Smallest machine for each size

The profile with the least memory that still has enough for the size's Q4 estimate, from the hardware catalog.

Smallest machine per Gemma 4 size
SizeSmallest Mac or PC-memory profileSmallest graphics-card profile
Gemma 4 E2BMac mini 2020 · M1 · 8 GBRTX 3050 · 6 GB
Gemma 4 E4BMac mini 2020 · M1 · 8 GBRTX 3050 · 8 GB
Gemma 4 12BMac mini 2020 · M1 · 16 GBRTX 3060 · 12 GB
Gemma 4 26B A4BMac mini 2024 · M4 · 32 GBRTX 3090 · 24 GB
Gemma 4 31BMac mini 2024 · M4 · 32 GBRTX 5090 · 32 GB

A dash means no profile of that kind in the catalog has enough memory for the size.

Memory by file precision

The same planning formula at three precisions (0.625, 1.125 and 2 bytes per parameter, plus working room and the system reserve). Estimates, not measurements.

Gemma 4 memory estimate by precision
Size
Gemma 4 E2B12*6*15*9*21*15*
Gemma 4 E4B14*8*19*13*28*22*
Gemma 4 12B171125193731
Gemma 4 26B A4B272143376963
Gemma 4 31B322650448276

* The model's page explains why its estimate differs.

Family tree

Family, sizes and, for each size, the two 4-bit files the tables use (GGUF Q4_K_M and MLX 4-bit) when one was collected. Other precisions are not drawn here.

Gemma 4 family: sizes and published filesSwipe sideways to see the files, or read the list below.
Gemma 4 family: sizes and published filesFamilySizesFilesGemma 4GoogleE2BGGUF Q4_K_M3.1 GBMLX 4-bit4.3 GBE4BGGUF Q4_K_M5 GBMLX 4-bit6.8 GB12BGGUF Q4_K_M7.1 GBMLX 4-bit6.7 GB26B A4B3.8B activeGGUF UD-Q4_K_M16.9 GBMLX 4-bit15.6 GB31BGGUF Q4_K_M18.3 GBMLX 4-bit18.4 GB

The same tree as a list:

  • Gemma 4 · Google
    • E2B
      • GGUF Q4_K_M · 3.1 GB · unsloth/gemma-4-E2B-it-GGUF, read Oct 23, 2026
      • MLX 4-bit · 4.3 GB · lmstudio-community/gemma-4-E2B-it-MLX-4bit, read Oct 23, 2026
    • E4B
      • GGUF Q4_K_M · 5 GB · unsloth/gemma-4-E4B-it-GGUF, read Oct 23, 2026
      • MLX 4-bit · 6.8 GB · lmstudio-community/gemma-4-E4B-it-MLX-4bit, read Oct 23, 2026
    • 12B
      • GGUF Q4_K_M · 7.1 GB · unsloth/gemma-4-12b-it-GGUF, read Oct 23, 2026
      • MLX 4-bit · 6.7 GB · lmstudio-community/gemma-4-12B-it-MLX-4bit, read Oct 23, 2026
    • 26B A4B · 3.8B active
      • GGUF UD-Q4_K_M · 16.9 GB · unsloth/gemma-4-26B-A4B-it-GGUF, read Oct 23, 2026
      • MLX 4-bit · 15.6 GB · lmstudio-community/gemma-4-26B-A4B-it-MLX-4bit, read Oct 23, 2026
    • 31B
      • GGUF Q4_K_M · 18.3 GB · unsloth/gemma-4-31B-it-GGUF, read Oct 23, 2026
      • MLX 4-bit · 18.4 GB · lmstudio-community/gemma-4-31B-it-MLX-4bit, read Oct 23, 2026

Learn more

Sources

Where the family and its sizes are named, and where each number comes from.