Qwen3.8-Max launches on DigitalOcean Serverless with 1M context

Alibaba_Qwen · x · 2026-08-14

Alibaba Cloud's Qwen3.8-Max (2.4T params, 95B active) is now available on DigitalOcean Serverless Inference, powered by NVIDIA HGX B300 GPUs, with 1M context for long-horizon coding. Usage-based pricing, no infra management.

Original post →

More from Models

Models channel →