Gemma 4 26B-A4B

At the default Q4_0, 3 of 140 phones have enough estimated usable memory; 3 also reach 3+ tokens/s. On Mac, 45 of 54 exact configurations pass using that quant or a smaller tracked fallback.

Params
26B (4B active)
Family
gemma
Released
2026-03
Tags
chat · vision · reasoning

Downloads & memory by quant

The download is only the weights — add KV cache and runtime to get what your phone actually needs. “Memory-fit” only means it can load; “usable” also requires an estimated 3+ tokens/s. Each row uses that row's quant. ★ = recommended.

QuantDownloadMemory neededPhone reality
Q4_014.4 GB~17.5 GB3 memory-fit · 3 usable

Gemma 4 26B-A4B at Q4_0 on 140 phones

This table is fixed to the recommended Q4_0, on each phone's largest RAM option. Counts for smaller quants above will differ. All phones are shown, sorted by fit and estimated experience; tap one for the full report.

PhoneChip · RAMNeedsSpeedVerdict

~ = bandwidth-based estimate · ✓ = measured on real hardware

Gemma 4 26B-A4B on 54 Mac configurations

Each Mac uses the recommended Q4_0 at 4K context when it fits, or the largest smaller tracked quant that fits. Each row links to the full report with a macOS-specific setup guide.

MacUnified memoryQuantWorking budgetNeedsEstimated speedVerdict

FAQ

How much RAM do I need to run Gemma 4 26B-A4B on a phone?

At Q4_0, Gemma 4 26B-A4B needs ~17.5GB of usable memory (weights + KV cache + runtime). In practice that means a 24GB+ Android phone or no current iPhone — iOS lets a single app use less of its RAM than Android does.

How fast does Gemma 4 26B-A4B run on a flagship phone?

On the OnePlus 13 (Snapdragon 8 Elite) it runs at ~15.6 tokens/s at Q4_0, estimated from memory bandwidth. Anything above ~8 tokens/s feels smooth for chat.

Can an iPhone run Gemma 4 26B-A4B?

Not really: the best iPhone we track (iPhone 16 Pro Max) has ~5.2GB usable, but Gemma 4 26B-A4B needs 17.5GB at Q4_0.

What is the best quantization of Gemma 4 26B-A4B for mobile?

Q4_0 (14.4GB download) is the size/quality sweet spot. Total memory needed is ~17.5GB once the KV cache and runtime are counted — the download size alone understates it.

How many phones can run Gemma 4 26B-A4B?

3 of the 140 phones we track have enough estimated usable memory at Q4_0; 3 also reach our usable-speed threshold of 3 tokens/s, and 3 run smoothly. Memory-fit alone does not mean a good experience.

Which Macs can run Gemma 4 26B-A4B?

45 of the 54 exact Mac configurations we track have enough estimated working memory. Each Mac uses the recommended Q4_0 when it fits, or the largest smaller tracked quant that fits, and separates installed unified memory, the macOS reserve, and estimated speed.

What is Gemma 4 26B-A4B good for on a phone?

It's tagged for chat, vision, reasoning. At 26B parameters (4B active — it's a MoE, so it decodes faster than its size suggests), it prioritizes answer quality over speed — expect slower decoding.

Similar models

Gemma 3 1BGemma 3 4BGemma 3 12BGemma 4 E2BGemma 4 E4B