Get the latest setups
Models/Gemma 4/Gemma 4 · 12B
Agents / Google DeepMind

Gemma 4 · 12B

A compact multimodal model that understands text, images, audio, and video for local assistants.

Verified sourceRepository opened May 23, 2026Source checked 9/23/2026
LOCALRENTED GPUOPEN WEIGHTS
Freshness 57 out of 100. Repository age: 145 days old, May 23, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,656,357 downloads in 30 days; 1,665 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source
Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source
Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method
WORKFLOWS FOR THIS MODEL 3

What do you want to do?

Choose a task. Get the software, files, settings, and steps to run it.

MAKE IT PERSONALChoose your hardware
Private chat

Set up private chat with Gemma 4 · 12B

Run a private local chat with Gemma 4 · 12B using Ollama on Windows, macOS, or Linux. You will install the runtime, fetch the 7.6 GB text-and-image model package, start a chat session, send a first prompt, and confirm the model responds.

Freshness 57 out of 100. Repository age: 145 days old, May 23, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,656,357 downloads in 30 days; 1,665 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Ollama
1 packagemacOS / Windows / Linux
Open chat guide
Image understanding

Ask questions about an image privately with Gemma 4

Use Gemma 4 12B through Ollama to answer questions about a local image without uploading it to a hosted model. Check its answer against the visible photo.

Freshness 57 out of 100. Repository age: 145 days old, May 23, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,656,357 downloads in 30 days; 1,665 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Ollama
1 packagemacOS / Windows / Linux
Open vision guide
Private chat

Set up private Gemma 4 chat

Choose official QAT packages for Gemma 4 E2B, E4B, or 12B, or a clearly marked community abliterated E4B package; follow Mac, Windows, or Linux instructions for your choice.

Freshness 57 out of 100. Repository age: 145 days old, May 23, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,656,357 downloads in 30 days; 1,665 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Ollama
1 packagemacOS / Windows / Linux
Opens with Gemma 4 12B · QATOpen chat guide

Open a guide for its software, hardware requirements, and setup steps.

At a glance

Parameters
12B
Architecture
Dense transformer
Context length
256,000
License
Apache 2.0
Disk space
7.6 GB
Software
Ollama, MLX, Transformers
View the model source
MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

  • Answer questions about private images on your computer.
  • Run local text and image tasks with an Ollama client.

Tradeoffs

  • Package size is not a measured VRAM requirement for image input.

Ways to run it

Ollama · Windows, macOS, Linux

Ollama lists a 7.6 GB text-and-image package. Image input and long context need their own memory check.

ollama run gemma4:12b
Official instructions

MLX · macOS

ollama run gemma4:12b-mlx
Official instructions

Explore its uses

AGENTSMULTIMODALCODINGRAG

Keep exploring

Agents
Z.ai

GLM 5.3

Explore 2 versions of GLM 5.3. Compare model sizes, packages, hardware requirements, and available setups.

2 versionsCompare sizes & formats
LOCALRENTED GPU
Compare versions →
Agents
Moonshot AI

Kimi K3

An open-weight multimodal model for long-running coding, reasoning, and knowledge work.

Freshness 62 out of 100. Repository age: 124 days old, Jun 13, 2026. Measures age, not quality.
Popularity 85 out of 100. 1,063,166 downloads in 30 days; 11,731 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Arena Open Source Agents: rank 7 of 18. Ranked model: Kimi K3 (Max). Export dated Oct 14, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+2
MODEL SIZE2.8T total · 104B active
LOCALRENTED GPU
Repository opened Jun 13, 2026
Agents
Qwen

Qwen3.5

Explore 3 versions of Qwen3.5. Compare model sizes, packages, hardware requirements, and available setups.

3 versionsCompare sizes & formats
LOCALRENTED GPU
Compare versions →