GOOGLE / 2026

Gemma 4 26B A4B IT

A compact multimodal MoE with 25.2B total and 3.8B active parameters, designed for accessible inference.

TOTAL PARAMETERS25.2B
ACTIVE / TOKEN3.8B
PINNED ARTIFACT51.6 GB
MAX CONTEXT256K

DECISION BRIEF

Single-accelerator baseline

The pinned BF16 checkpoint carries 51.6 GB of tensors, clearing the static baseline on one 80 GB accelerator while still requiring runtime validation.

WEIGHTSOpen weights

Publicly available checkpoints; verify terms before commercial deployment.

LICENSEUnverified in registry

Unknown remains explicit until the exact checkpoint license is verified and sourced.

EVIDENCEPrimary source

Architecture values are linked to the publishing organization.

ARCHITECTURE

Compute is sparse. Residency is not.

The pinned BF16 checkpoint carries 51.6 GB of tensors, clearing the static baseline on one 80 GB accelerator while still requiring runtime validation.

Expert topology: 128 / top-8. The active-parameter count approximates token-level compute; it does not determine checkpoint memory, KV-cache demand, expert placement, or interconnect pressure.

PRIMARY SOURCE

Google introduces Gemma 4

Inspect evidence
PINNED ARTIFACT

google/gemma-4-26B-A4B-it@4d7ae4984b7d · 51.6 GB

Open manifest

NEXT ACTION

Test the workload, not the headline.

Start with checkpoint residency, then layer in context, concurrency, runtime overhead, topology, and resilience.

Build an assurance plan