Skip to content

feat(ai): add Ollama (stable ollama-cpu, CPU-only)#22

Merged
UnbreakableMJ merged 1 commit into
mainfrom
feat/ollama-cpu
Jul 2, 2026
Merged

feat(ai): add Ollama (stable ollama-cpu, CPU-only)#22
UnbreakableMJ merged 1 commit into
mainfrom
feat/ollama-cpu

Conversation

@UnbreakableMJ

Copy link
Copy Markdown
Contributor

Re-adds the local LLM runtime (removed in #18) as ollama-cpu — CPU-only, since the ThinkPad has no discrete GPU.

From stable, not unstable: the pinned nixpkgs-unstable input currently ships ollama 0.21.1, which is older than stable 26.05's 0.24.0. So stable is the newer choice here (verified). Package only — run ollama serve (no services.ollama module, matching the prior setup).

Toplevel builds with ollama-0.24.0 in the closure.

🤖 Generated with Claude Code

Re-add the local LLM runtime (removed in #18), CPU-only for this dGPU-less
ThinkPad. Sourced from stable pkgs, not unstable: the pinned nixpkgs-unstable
input currently ships ollama 0.21.1, which is OLDER than stable 26.05's 0.24.0,
so stable is the newer choice here. Package only — run `ollama serve` (no
services.ollama module, matching the prior setup).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@UnbreakableMJ UnbreakableMJ merged commit b00ddd7 into main Jul 2, 2026
1 check passed
@UnbreakableMJ UnbreakableMJ deleted the feat/ollama-cpu branch July 2, 2026 09:58
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant