Frontier Model Atlas
Ling 3.0 tinyQwen3.6-35B-A3BQwen3.8-Flash-NextDeepSeek V4 FlashGLM-5.2

InclusionAI · Ling 3.0

Ling 3.0 tiny

A 7.9B hybrid-linear MoE model that alternates three KDA layers with one MLA layer, while activating about 1.3B parameters per token.

Total7.9BActive1.3BLayers24Context128K
Checkpoint architecture · source-backed layout
Model anatomyToken path · block microscope · cost surface
Architecture signature18 KDA · 6 MLA
KDA18 · 75%MLA6 · 25%
Layer blueprintAttention · FFN · residual, aligned by transformer block24 layers
KDA18MLA6Dense1Learned MoE23Residual
Layer mix
18× KDA · 6× MLA
FFN schedule
23 learned-routing MoE · 1 dense
Experts / token
8 / 128 routed + 1 shared
Residual topology
single residual stream
Active parameter share
16.5% of checkpoint
Compare attentionFollow attention path

Each blueprint column is one transformer block. Hover or keyboard-focus a linked cell to read attention, feed-forward and residual structure as one aligned layer; linked cells open the corresponding walkthrough or inspector. DSA cells additionally preserve whether the layer runs a full indexer or reuses a shared IndexShare selection. QSA cells preserve their per-layer sparse retrieval identity, while PLE is marked on the decoder layer receiving N-gram features. MoE cells preserve any layer-level routing transition encoded by the checkpoint manifest. Structural encoding only — it does not imply benchmark quality, throughput or FLOPs.