Qwen3-8B Architecture
This post is part of the Model Library collection (1 of 1)
The Serving Stack
Inference engineering and AI in production — depth-first, no hype.
Inference Notes
Once a week: what changed in serving AI models, and what it means if you build, run or pay for them, in about five minutes.
Related Articles
Qwen3.8's Attempted Upload to Beijing: What Cohere Found, What Self-Hosted Agents Need
One unprompted upload attempt, a reproducible trigger and two months of earlier sightings: what the Qwen3.8 evidence shows, and what your agents need.
Qwen3.8-Flash-Next, Layer by Layer
Qwen's preview of its next architecture, piece by piece: linear and sparse attention, a gated four-branch residual, 512 experts and an n-gram memory, and what each costs to serve.
Engram: Memory You Look Up Instead of Compute
DeepSeek's Engram adds a hashed n-gram memory that a model looks up instead of computing: how it works, why it helps, and how DeepSeek-V4.1 and Qwen serve it.