specific method · filed under model architecture
Gated DeltaNet MoE
An MoE architecture identified by its use of gated delta networks.
Also called gated-delta-networks MoE architecture, routed and shared experts in MoE, 256 experts, 8 routed + 1 shared.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
sharing the same gated-delta-networks MoE architecture but with 35B total parameters and 3B activated (256 experts, 8 routed + 1 shared)
coreunclearin Qwen3.6-35B-A3BQwen
256 experts, 8 routed + 1 shared
coreunclearin Qwen3.6-35B-A3BQwen
Filed alongside
Other methods under model architecture :: channel mixer :: mixture of experts.
Mixture of ExpertsSparse expert activationDeepSeekMoEMixture-of-Experts layersMoE with routed and shared expertsAsymmetric input/output activation splitDispatch recomputationFrequency-based partitioning of N-gram embedding slotsHybrid Mixture of ExpertsMegaMoEMoE with 128 routed experts and a shared expertMoE with 256 experts and top-8 routingMoE with 384 routed experts and a shared expertOutput-independent MoE gradient reformulationRouted expert output modulationSigmoid-based MoE router with auxiliary-loss-free load balancing