Latest Content

Model Guides

Updated on 12 March, 2026

Deploy large AI models including DeepSeek V3.2, Llama 3.1, Qwen3-VL, and Kimi-K2.5 on AMD Instinct GPUs.

DeepSeek V3.2 (685B)
Deploy DeepSeek V3.2 (685B parameters) on AMD Instinct GPUs.
Llama 3.1 (405B)
Deploy Meta's Llama-3.1-405B-Instruct on AMD Instinct GPUs.
Qwen3-VL (235B)
Deploy Qwen3-VL-235B-A22B-Instruct (Vision-Language model) on AMD Instinct GPUs.
Kimi-K2.5 (1T)
Deploy Kimi-K2.5 (1 trillion parameters) on AMD Instinct GPUs.