Qwen3.8-Max launches on Fireworks with Day-0 support: 2.4T-param MoE for agents and coding
Alibaba_Qwen · x · 2026-08-14
Alibaba's Qwen team announced Qwen3.8-Max is now live on Fireworks with Day-0 support. The 2.4T-parameter MoE model is built for autonomous agents, heavy coding, and long-context work. Fireworks is a launch partner, offering immediate availability.
More from Models
- Qwen3.8-27B community feedback: memory, speed, and creative writing questions — pmttyji · 2026-08-15
- Qwen3.8-27B benchmark: BF16 TP2 performance data — Maleficent_Bridge_41 · 2026-08-15
- Qwen3.8-27B Test: SVG Generation Takes 7m15s, Config Shared — Fz1zz · 2026-08-15
- Qwen3.8-27B launches with day-zero AMD support for local AI development — Alibaba_Qwen · 2026-08-15
- Qwen3.8-27B Code Review Test: Good Analysis but Half Reasoning Tokens Wasted — Ok-Shower7286 · 2026-08-15
- Benchmark Request: Qwen3.8-27B Full Precision & FP8 on RTX 6000 Pro with vLLM — HumanDrone8721 · 2026-08-15