Together AI 已在其 Serverless Inference 平台上发布了 Qwen3.8-2.4T-A95B，这是 Qwen 团队的新旗舰模型。该模型专为编码和长时代理工作流设计，拥有 2.4 万亿参数和巨大的上下文窗口。它提供了任务状态恢复和自我测试等功能，旨在提高模型在复杂任务上的代理性能。 AI
影响 通过庞大的参数数量和上下文窗口，增强了编码和长时代理工作流的能力。
排序理由 前沿实验室（Qwen 团队）在推理平台（Together AI）上发布模型。
在 X — Together (inference / OSS) 阅读 →
AI 生成摘要 · Google Gemini · 来自 9 个来源。 我们如何撰写摘要 →
RT @Alibaba_Qwen: Qwen3.8-Max is live on Together AI. Together AI is with us as a Day 0 launch partner, and we couldn’t ask for a better na…
Qwen3.8-2.4T-A95B is live on Together AI. The Qwen team’s new open-weight MoE packs 2.4T total parameters with 95B active, a 1M context window, and strong coding & agent capabilities. Start building: https://t.co/3NiCaug5Im
Qwen3.8-Max is live on Together AI on day zero. Proud to have supported early testing alongside @Alibaba_Qwen, @vllm_project, and Inferact to get day-zero support live. We’re continuing to optimize performance from here. Stay tuned! Start building: https://t.co/3NiCaug5Im
Together Serverless Inference gives developers a managed, high-throughput path for running Qwen3.8-2.4T-A95B across coding and agentic workloads. Start building: https://t.co/3NiCaufxSO
What Qwen3.8-2.4T-A95B brings to long-running agents: → 256K context for large codebases and extended workflows → Task state, dispatch, and recovery across coding loops → Self-testing across builds, unit tests, and E2E tests → Function calling and structured outputs
Qwen3.8-2.4T-A95B is now live on Together AI. The Qwen Team’s latest flagship model is built for coding and long-horizon agent workflows, with 2.4T parameters and a 256K context window. 🧵 https://t.co/elR1hJiCHt
Together Serverless Inference gives developers a managed, high-throughput path for running Qwen3.8-2.4T-A95B across coding and agentic workloads. Start building: https://t.co/3NiCaufxSO
Qwen3.8-2.4T-A95B is now live on Together AI. The Qwen Team’s latest flagship model is built for coding and long-horizon agent workflows, with 2.4T parameters and a 1M context window. 🧵 https://t.co/rauwliZDAD
What Qwen3.8-2.4T-A95B brings to long-running agents: → 1M context for large codebases and extended workflows → Task state, dispatch, and recovery across coding loops → Self-testing across builds, unit tests, and E2E tests → Function calling and structured outputs