In the news
Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72
NVIDIA Developer · Published · 3 min read
In 30 seconds
- What happened
- Alibaba's Qwen3.8-2.4T-A95B, a 2.4 trillion parameter open-weight model, now runs optimized on NVIDIA GB300 NVL72 hardware with configurable reasoning controls.
- Why it matters
- Engineers deploying large language models in production need efficient inference at scale, especially for agentic AI workloads like code generation and document analysis.
- Watch out
- The 4K tokens per second throughput requires NVIDIA's specialized GB300 NVL72 hardware with 72 GPUs; performance on other systems will differ significantly.
Listen to this summary
- reasoning
- context window
- attention
- token
- mixture of experts
The patterns behind this
- Agentic Context Engineering (Evolving Playbook)
- Energy-Efficient Inference
- Generative UI (Agent-Rendered Interfaces)
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.