gemma
26B parameters
Commercial OK
Reviewed July 2026

Gemma 4 26B-A4B

Gemma 4 26B-A4B is Google's MoE variant of the Gemma 4 family (26B total, 4B active), released alongside the dense Gemma 4 lineup in 2026. The 4B active-parameter footprint gives faster decode than the dense 12B/31B siblings at a similar quality tier.

License: Gemma Terms of Use·Context: 131,072 tokens

Overview

Gemma 4 26B-A4B is Google's MoE variant of the Gemma 4 family (26B total, 4B active), released alongside the dense Gemma 4 lineup in 2026. The 4B active-parameter footprint gives faster decode than the dense 12B/31B siblings at a similar quality tier.

Strengths

  • MoE design decodes faster than dense Gemma 4 siblings at comparable quality
  • Gemma Terms of Use permits commercial deployment
  • Fits fully in 24-32GB VRAM at Q4_K_M with context headroom

Weaknesses

  • 26B total weight footprint (16GB Q4) exceeds most consumer 16GB cards' comfortable margin
  • Less real-world adoption data than the dense 12B Gemma 4 variant
BLK · QUALITY BENCHMARKreviewed · raw logs

Reviewed quality benchmarks

First-party rows were run by RunLocalAI; reviewed community rows are labeled in the data. Every row links to the raw test-run log.

BenchmarkQuantRuntime / HardwareScoreRaw log
HumanEval+
tested 2026-07-20
Q4_K_M
ollama-0.32.1-vast5090
rtx-5090
93.3/100
Gist →

Q4_K_M note:First-party HumanEval+ on a rented Vast.ai RTX 5090 32GB instance via Ollama 0.32.1. Generation via evalplus_openai_generate.py, scoring via evalplus.evaluate (native Linux, no Windows shim needed). No DB credentials were placed on the rented host — results were pulled back and ingested from the operator's machine.

Want to verify? Every row links to its Gist with full stdout and stderr of the run. The runner script is in the public repo (scripts/run-humaneval-plus.ts) — reproducible end-to-end. Browse all coding scores at /benchmarks/coding.

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M16.0 GB20 GB

Get the model

Ollama

One-line install

ollama run gemma4:26b-a4b-it-q4_K_MRead our Ollama review →

Hardware that runs this

Cards with enough VRAM for at least one quantization of Gemma 4 26B-A4B.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Frequently asked

What's the minimum VRAM to run Gemma 4 26B-A4B?

20GB of VRAM is enough to run Gemma 4 26B-A4B at the Q4_K_M quantization (file size 16.0 GB). Higher-quality quantizations need more.

Can I use Gemma 4 26B-A4B commercially?

Yes — Gemma 4 26B-A4B ships under the Gemma Terms of Use, which permits commercial use. Always read the license text before deployment.

What's the context length of Gemma 4 26B-A4B?

Gemma 4 26B-A4B supports a context window of 131,072 tokens (about 131K).

How do I install Gemma 4 26B-A4B with Ollama?

Run `ollama pull gemma4:26b-a4b-it-q4_K_M` to download, then `ollama run gemma4:26b-a4b-it-q4_K_M` to start a chat session. The default quantization is Q4_K_M.

Source: Vendor official documentation

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Before you buy

Verify Gemma 4 26B-A4B runs on your specific hardware before committing money.