taxonomy node · level 2
context capacity
10 methods filed at this node or below it, from the sources of 9 models.
model architecture :: context capacity
Matching aids for the classifier: 1M context window; long context window; conditional memory; Engram.
In this branch 10
Everything filed at this node or below it, with one collapsible heading per child node.
filed here 10
By model
Which of this branch's techniques each model's own documents describe, and how strongly. Under each model: its strongest treatment anywhere in the branch.
| Model | techniques |
|---|---|
| DeepSeek-V4.1-Flash core | Engram coreRow-wise distributed partitioning of embedding tables used— |
| MiMo-V2.6-Flash core | 1M-token context window core— |
| DeepSeek-V4-Flash default | 1M-token context window default— |
| MiMo-V2.5 used | 1M-token context window usedProgressive context extension used— |
| DeepSeek-V4-Pro default | 1M-token context window defaultEngram not used— |
| Kimi K3 used | Progressive context extension used— |
| MiMo-V2.5-Pro used | 1M-token context window usedProgressive context extension used— |
| Qwen3.8-Flash-Next core | N-gram embedding host-memory offload and prefetch coreN-gram embedding lookup coreSingle-layer N-gram embedding placement coreMulti-head hashing usedToken normalization for N-gram vocabulary compression evaluated— |
| Step-3.7-Flash core | 256K context window core— |