DeepSeek V4 / V4.1
DeepSeek
Flash evolves from a post-training update into a different memory system.
ERNIE / Lab profile
A base release opens an adaptation path.
First time comparing models? Learn the terms before the architecture →
ERNIE 5.5 Flash Base is a pretrained text checkpoint. Its training stage and custom license are first-order selection constraints before any serving comparison.
Architecture trajectory
The 43-layer backbone mixes 37 hierarchical compressed-attention layers with six sparse latent-attention layers. Compression applies to particular representations, not automatically to all cache allocations.
Sparse reads do not imply proportional storage savings.
Sum both layer families before adding runtime overhead.
Newest first / grouped sequence, not a time scale
Start with the training stage and license
Thirty-seven hierarchical compressed-attention layers group history at a 128-token ratio; six MLA-DSA layers use a different retained representation. The whole cache does not shrink by 128 times.
The applicable model license identifies November 5 as its release date; the repository existed earlier.
DeepSeek and Ling are useful architectural comparisons, but their post-trained checkpoints serve a different starting point for application development.
DeepSeek V4 / V4.1
Flash evolves from a post-training update into a different memory system.
Ling
Hybrid state and checkpoint identity decide the rollout.
Interview preparation
Distinguish total weights, active computation, extra ECHO parameters, training context and configured positions.
Study the underlying systems → · Get the illustrated report →
Covered checkpoints carry their own research dates. Assessments and comparison candidates are our interpretation of the cited designs, not measured cross-lab rankings. Each timeline entry links to its release evidence; model pages preserve pinned card and configuration sources.