Unverified50% confidenceFactExact time
The current version of Ollama is v0.40.3, and the official images support NVIDIA CUDA, AMD ROCm and the built-in Vulkan runtime.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedThe new version adds AMD ROCm images for Linux hosts, available alongside CUDA images71% similarVerifiedOllama supports CPU AVX2/AVX512 instruction set acceleration, as well as multiple GPU backends including NVIDIA CUDA, Apple Metal, and AMD ROCm.69% similarUnverifiedTokenSpeed requires an NVIDIA GPU host (the nightly wheel requires CUDA 13) or an AMD host with ROCm 7.2, and Python 3.11 to 3.13.69% similarUnverifiedOllama can be deployed via Docker, with official documentation covering three environments: CPU-only, NVIDIA GPU, and AMD GPU.68% similarUnverifiedllama.cpp uses CUDA on NVIDIA GPUs, ROCm on AMD GPUs, and Metal on Apple silicon.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1058317API
curl https://kongchang.com/api/v1/knowledge/claims/1058317MCP
get_claim(id=1058317)