🔥36氪•較早收集於 4m
摩爾線程 MTT S5000 全面適配阿里 Qwen3.5 三款新模型
#gpu-adaptation#open-models#domestic-hardwaremtt-s5000moore-threadsmtt-s5000qwen3.5alibaba
💡Run Alibaba's latest open LLMs on Chinese GPU without Nvidia dependency (mid-scale models now supported)
⚡ 30-Second TL;DR
有什麼變化
MTT S5000 支援 Qwen3.5-35B-A3B、Qwen3.5-122B-A10B、Qwen3.5-27B
為什麼重要
此舉提升中國本土 AI 硬體選擇，減少對外國 GPU 的依賴，用於運行阿里開源模型。AI 從業者獲得部署中規模 LLM 的具成本效益替代方案。
下一步行動
Download Qwen3.5-122B-A10B and test inference benchmarks on MTT S5000 hardware.
誰應關注：Developers & AI Engineers
關鍵要點
- •MTT S5000 支援 Qwen3.5-35B-A3B、Qwen3.5-122B-A10B、Qwen3.5-27B
- •摩爾線程 GPU 實現 AI 訓練與推論的全方位適配
- •繼阿里開源中等規模 Qwen3.5 模型之後
- •2 月 26 日透過官方微博宣布
🧠 深度解析
背景與延伸：來自公開資料，非原文內容。引用 5 個來源。
🔑 增強重點摘要
- •Moore Threads demonstrated DeepSeek V3 performance on the MTT S5000, achieving 1000 tokens per second in Decode and 4000 tokens per second in Prefill, slightly ahead of Nvidia's Hopper lineup.[1]
- •MTT S5000 was used in benchmarks by 51WORLD's next-gen simulation platform, showing approximately 1.47× performance gains in FP32, FP16, and INT8 precision modes.[5]
- •Preceding the S5000, Moore Threads' MTT S4000 GPU with 128 Tensor Cores and 48GB memory already supported Qwen models for training and inference via its MUSA architecture.[3]
🔮 前景展望AI analysis grounded in cited sources
Moore Threads MTT S5000 will expand adoption of domestic Chinese AI GPUs in model training ecosystems.
Full adaptation of Alibaba's Qwen3.5 models enables comprehensive training and inference support on MTT S5000, building on prior Qwen compatibility in S4000 and recent DeepSeek V3 benchmarks outperforming Hopper.
This adaptation strengthens Moore Threads' position against Nvidia in China's AI compute market.
MTT S5000's demonstrated superior DeepSeek V3 inference speeds compared to Hopper, combined with Qwen3.5 support, highlights competitive performance for large model workloads.
⏳ 時間線
2026-02
MTT S4000 supports Qwen for LLM training and inference with 128 Tensor Cores.
2026-02
MTT S5000 demonstrates DeepSeek V3 inference at 1000 tps Decode and 4000 tps Prefill.
2026-02
51WORLD simulation platform benchmarks MTT S5000 with 1.47× gains in key precisions.
2026-02
Moore Threads announces full adaptation of Qwen3.5 models on MTT S5000.
📎 來源 (5)
Factual claims are grounded in the sources below. Forward-looking analysis is AI-generated interpretation.
- Tom's Hardware — Moore Threads Unveils Next Gen Gaming GPU with 15x Performance and 50x Ray Tracing Improvement AI GPU with Claimed Performance Between Hopper and Blackwell Also in the Works
- notebookcheck.net — China S Moore Threads Unveils Huagang GPU Architecture with Claimed 15x Gaming and 50x Ray Tracing Boost.1190382.0
- en.mthreads.com — S4000
- en.overclocking.com — Moore Threads a Dx12 Ultimate Gaming GPU Ready to Break All Records in 2026
- pandaily.com — 51 World S Next Gen Simulation Platform Fully Adapts to Moore Threads Flagship GPU
📰
AI 週報
閱讀本週精選 AI 大事摘要 →
👉相關動態
AI 策展新聞聚合。所有內容版權歸原始發布者所有。
原始來源： 36氪 ↗
每週 AI 簡報
每週一封，可隨時退訂。