繁體中文
繁體中文
Model
/
LLM
/
DeepSeek
DeepSeek R1
GMI Cloud 引領 AI 新時代
GMI Cloud 為 AI 創新者提供最先進的 NVIDIA GB200 NVL72 平台，在大型語言模型（LLM）推理、向量資料庫搜尋和資料處理方面帶來突破性的效能。GB200 NVL72 搭載雙 Blackwell GPU 和 NVIDIA NVLink® 互連技術，專為處理大規模 AI 工作負載而設計，並透過 NVIDIA 的可擴展 MGX™ 架構，輕鬆整合至現有基礎設施。結合 GMI Cloud 和 NVIDIA GB200 NVL72，讓您能更智慧地擴展規模，加速創新，充分發揮運算潛力。initial takeaways here.
Technical details:
Model Provider:
DeepSeek
Type:
Chat
Parameters:
685B
Deployment:
Serverless (MaaS) or Dedicated Endpoint
Quantization:
FP16
Context Length:
Up to 128,000 tokens
Distilled models offering:
- DeepSeek-R1-Distill-Llama-70B
- DeepSeek-R1-Distill-Qwen-32B
- DeepSeek-R1-Distill-Qwen-14B
- DeepSeek-R1-Distill-Llama-8B
- DeepSeek-R1-Distill-Qwen-7B
- DeepSeek-R1-Distill-Qwen-1.5B
Try our token-free service with unlimited usage!
Reach out for access to our dedicated endpoint Here.
訂閱 GMI Cloud 電子報
Empowering humanity's AI ambitions with instant GPU cloud access.
2860 Zanker Rd. Suite 100 San Jose, CA 95134
