[PR #14999] [CLOSED] add MoltenVK support for Intel macs #14960

Closed
opened 2026-04-13 01:06:55 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/14999
Author: @jamfor999
Created: 3/21/2026
Status: Closed

Base: mainHead: main


📝 Commits (6)

  • cfc633a feat: initial amdgpu support for macOS Intel. Experimental
  • b6e46a5 Merge branch 'ollama:main' into main
  • bc82a55 Merge branch 'ollama:main' into main
  • 6ab3bab Merge branch 'main' of github.com:ollama/ollama
  • c521dd0 Merge branch 'ollama:main' into main
  • 0842460 Merge branch 'ollama:main' into main

📊 Changes

5 files changed (+421 additions, -1 deletions)

View changed files

📝 CMakeLists.txt (+17 -1)
📝 CMakePresets.json (+12 -0)
📝 README.md (+19 -0)
cmake/OllamaMoltenVK.cmake (+135 -0)
scripts/build_darwin_vulkan.sh (+238 -0)

📄 Description

Created this fork a while back as part of this issue: https://github.com/ollama/ollama/issues/1016

There are still users of Intel Macs with AMD GPUs and while macOS support is being deprecated, people still like to use macOS, and it will still have Security support for quite a while (plus I highly suspect it'll live on some way or another, although thats a whole other thing...)

Seems like users are happy with my fork, its had a number of stars and no real reported issues over the past few months, so I'm happy to contribute this upstream at this stage, it should not cause issues for other users


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/14999 **Author:** [@jamfor999](https://github.com/jamfor999) **Created:** 3/21/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (6) - [`cfc633a`](https://github.com/ollama/ollama/commit/cfc633ae9e9d0195d5dd09a918b60a7ed513ba3a) feat: initial amdgpu support for macOS Intel. Experimental - [`b6e46a5`](https://github.com/ollama/ollama/commit/b6e46a5e0714f6e06dc802d812d8a5e92b20a3a5) Merge branch 'ollama:main' into main - [`bc82a55`](https://github.com/ollama/ollama/commit/bc82a5507ed2f7439966d9409d678800a0d097fe) Merge branch 'ollama:main' into main - [`6ab3bab`](https://github.com/ollama/ollama/commit/6ab3babf9df0ff371f932a1b34fe88f7423491b9) Merge branch 'main' of github.com:ollama/ollama - [`c521dd0`](https://github.com/ollama/ollama/commit/c521dd0493ce7af720f297faaa47fd665185c637) Merge branch 'ollama:main' into main - [`0842460`](https://github.com/ollama/ollama/commit/084246040a6a841f52031d2a8677297e4fe545bb) Merge branch 'ollama:main' into main ### 📊 Changes **5 files changed** (+421 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `CMakeLists.txt` (+17 -1) 📝 `CMakePresets.json` (+12 -0) 📝 `README.md` (+19 -0) ➕ `cmake/OllamaMoltenVK.cmake` (+135 -0) ➕ `scripts/build_darwin_vulkan.sh` (+238 -0) </details> ### 📄 Description Created this fork a while back as part of this issue: https://github.com/ollama/ollama/issues/1016 There are still users of Intel Macs with AMD GPUs and while macOS support is being deprecated, people still like to use macOS, and it will still have Security support for quite a while (plus I highly suspect it'll live on some way or another, although thats a whole other thing...) Seems like users are happy with my fork, its had a number of stars and no real reported issues over the past few months, so I'm happy to contribute this upstream at this stage, it should not cause issues for other users --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-13 01:06:55 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#14960