QWEN TEAM / 2025

Qwen3-30B-A3B

A 30.5B-parameter reference MoE with 3.3B active parameters and a broadly accessible artifact footprint.

TOTAL PARAMETERS30.5B
ACTIVE / TOKEN3.3B
PINNED ARTIFACT61.1 GB
MAX CONTEXT32K

DECISION BRIEF

Accessible MoE development

Eight of 128 experts activate per token. The exact pinned BF16 manifest is 61.1 GB, making it a practical reference case for the residency engine.

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.

Eight of 128 experts activate per token. The exact pinned BF16 manifest is 61.1 GB, making it a practical reference case for the residency engine.

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

Qwen3

Inspect evidence
PINNED ARTIFACT

Qwen/Qwen3-30B-A3B@ad44e777bcd1 · 61.1 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