Unverified50% confidenceFactExact time
Ollama began integrating ROCm support starting from version 0.1.14, but ROCm support on Windows remains less stable than on Linux.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
Valid until: 10/20/2026
Sources
Ollama本地部署大模型：Windows完整安装教程
Related Claims
UnverifiedROCm is an open-source GPU computing platform launched by AMD in 2016; the current ROCm 6.x version already provides official support for PyTorch and TensorFlow.70% similarUnverifiedAMD's ROCm platform was launched in 2016, providing HIP as a compatibility layer for CUDA, and PyTorch officially provides precompiled packages for ROCm.63% similarVerifiedOllama supports CPU AVX2/AVX512 instruction set acceleration, as well as multiple GPU backends including NVIDIA CUDA, Apple Metal, and AMD ROCm.61% similarUnverifiedOllama wraps a REST API and model management functionality on top of llama.cpp, and llama.cpp supports multiple hardware backends including CUDA, Metal, Vulkan, and ROCm.61% similarUnverifiedOllama simultaneously manages three GPU computing stacks—NVIDIA CUDA, AMD ROCm, and Apple Metal—through a unified abstraction layer.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/590882API
curl https://kongchang.com/api/v1/knowledge/claims/590882MCP
get_claim(id=590882)