Search Criteria
Package Details: ollama-cuda12-bin 0.40.3-1
Package Actions
| Git Clone URL: | https://aur.archlinux.org/ollama-bin.git (read-only, click to copy) |
|---|---|
| Package Base: | ollama-bin |
| Description: | Create, run and share large language models (LLMs) with CUDA 12 |
| Upstream URL: | https://github.com/ollama/ollama |
| Keywords: | ai llm local |
| Licenses: | MIT |
| Conflicts: | ollama-cuda, ollama-cuda13, ollama-vulkan |
| Provides: | ollama-cuda12 |
| Submitter: | Dominiquini |
| Maintainer: | Dominiquini (csjewell) |
| Last Packager: | Dominiquini |
| Votes: | 8 |
| Popularity: | 0.36 |
| First Submitted: | 2025-09-26 06:29 (UTC) |
| Last Updated: | 2026-10-11 13:30 (UTC) |
Dependencies (5)
- nvidia-libgl (nvidia-410xx-utilsAUR, nvidia-440xx-utilsAUR, nvidia-430xx-utilsAUR, nvidia-340xx-utilsAUR, nvidia-510xx-utilsAUR, nvidia-utils-teslaAUR, nvidia-575xx-utilsAUR, nvidia-535xx-utilsAUR, nvidia-525xx-utilsAUR, nvidia-390xx-utilsAUR, nvidia-470xx-utilsAUR, nvidia-550xx-utilsAUR, nvidia-production-utilsAUR, nvidia-580xx-utilsAUR, nvidia-vulkan-utilsAUR, nvidia-utils-betaAUR, nvidia-utils-g2AUR, nvidia-utils)
- ollama-binAUR
- ollama-cuda12 (ollama-cuda12-binAUR) (optional) – NVIDIA GPU Support
- ollama-cuda13 (ollama-cuda13-binAUR) (optional) – NVIDIA GPU Support
- ollama-vulkan (ollama-vulkan-gitAUR, ollama-vulkan-binAUR) (optional) – GPU Support
Required by (4)
- ollama-bin (requires ollama-cuda12) (optional)
- ollama-cuda12-bin (requires ollama-cuda12) (optional)
- ollama-cuda13-bin (requires ollama-cuda12) (optional)
- ollama-vulkan-bin (requires ollama-cuda12) (optional)
Latest Comments
1 2 3 Next › Last »
tiziodcaio commented on 2026-10-06 15:26 (UTC)
https://wiki.archlinux.org/title/AUR_submission_guidelines#Rules_of_submission I'd like to remember rule #1 especially after the AUR supply chain attacks...
csjewell commented on 2026-10-06 14:44 (UTC) (edited on 2026-10-06 14:46 (UTC) by csjewell)
@tiziodcaio: There is actually 3 "packaging variants" of ollama available for ArchLinux, and anyone can choose which one to use based on the speed and willingness to be possibly broken that they have.
ollama and ollama-* on extra: Official ArchLinux packages, goes through that process after a release happens, could be slower to update. They build particular tags from the git repository in ollama's case, although usually official packages will build from source tarballs.
ollama-bin and ollama-*-bin on AUR: This package, downloads the prebuilt binaries from https://github.com/ollama/ollama/releases (as opposed to ArchLinux building them.) We TRY to update this package pretty quickly after a new release, and occasionally we will need to fix the packaging beyond just putting in new SHAs and versions as well. Ollama itself pushes new releases frequently (weekly or so, IIRC) and this package follows that.
ollama-git and ollama-*-git on AUR: That package uses git to pull the CURRENT SOURCE from GitHub from the 'main' branch (not any particular release, just the HEAD commit) at https://github.com/ollama/ollama and builds it, so it's "on the bleeding edge" if you will. If the 'main' branch is broken, the -git packages will be, also, so people using -git packages need to take that into account.
Dominiquini commented on 2026-10-05 23:31 (UTC)
@tiziodcaio: I created this package primarily to provide the 'vulkan' version of ollama, as it didn't exist in the 'extra' section for a while. Now that it's been published there, I don't really see much point in keeping this package. I only continue maintaining it because it costs me almost nothing...
tiziodcaio commented on 2026-10-05 17:20 (UTC)
Has it any difference from the package in extra repo? https://archlinux.org/packages/extra/x86_64/ollama/
ticpu commented on 2026-08-14 19:54 (UTC)
I can help in maintaining the latest version if you wish.
csjewell commented on 2026-08-13 14:09 (UTC) (edited on 2026-08-13 14:10 (UTC) by csjewell)
I want to say "Please give Dominiquini (and I, although he's fast enough I don't do much) 48 or 72 hours before marking it out-of-date, please." There's only so much time in a day, after all, and I have even less, plus ollama pushes new builds up FREQUENTLY.
omnigenous commented on 2026-07-29 09:12 (UTC)
kodx commented on 2026-05-23 17:32 (UTC) (edited on 2026-05-23 17:32 (UTC) by kodx)
For CUDA 12, I had to patch the libggml-cuda.so library, otherwise the program couldn't find other libraries in the directory. This should be done after installing the program. Here are the commands:
Installing patchelf
Patching the library to add $ORIGIN to rpath
Another option is to add
/usr/lib/ollamato ldconfig, but this should be considered harmfull and lead to errors with other sofrware.This error is in upstream ollama binary libs.
xenoxaos commented on 2026-05-08 00:08 (UTC)
I had to roll back to f450a5df747d to rebuild 0.22.1 in order to get it working on my 1070 ti.
csjewell commented on 2026-05-07 05:11 (UTC)
Looks good, and thank you!
1 2 3 Next › Last »