BSD Ports

ai/ollama 0.34.3 MidnightBSD

Run text/image LLMs and programming APIs locally and in the cloud

System
MidnightBSD
Repository
mports
Maintainer
[email protected]
Last update
Commit
3bb1790d8a
License
mit
Categories
ai

Description

Ollama is a tool that allows you to get up and running with large language models locally. It provides a simple command-line interface to run and manage models, as well as a REST API for programmatic access.

Ollama supports a wide range of models available on ollama.com/library, including popular models like Llama 3, Gemma, and Mistral. It also allows you to customize models and create your own.

With Ollama, you can:

  • Run large language models on your own machine
  • Chat with models in the terminal
  • Generate text and embeddings
  • Customize models with your own prompts and data
  • Expose models through a REST API for use in your applications
  • Run generative models that generate images

In the other systems

The newest version among them is 0.40.11, as upstream numbers it.

SystemPortVersionVulnerabilitiesStatusMaintainerLast update
MidnightBSDai/ollama0.34.3 behind since 2026-10-07no data-[email protected]2026-10-09
FreeBSDmisc/ollama by name0.40.11 newestnone known-[email protected]2026-10-24
HardenedBSDmisc/ollama by name0.34.3 behind since 2026-10-07no data-[email protected]-
GhostBSDmisc/ollama by name0.34.0 behind since 2026-09-22no data-[email protected]-

Version history 1

  1. 0.34.3 3bb1790d8a

Upstream's version as each commit to the port's Makefile set it, or as this site first saw it in the system's packages; the tree's own revisions are not versions here.

Install

Binary package:

mport install ollama

From mports:

cd /usr/mports/ai/ollama && make install clean

To depend on this port in another port's Makefile:

RUN_DEPENDS=	ollama>0:ai/ollama

Dependency graph

Ports that need it on the left, what it needs to run on the right (to build, as it needs nothing to run); at most 8 of each. "Dependencies" below lists them all.

Dependencies

As this port's Makefile names them.

Build 5

Build dependencies 5

No port depends on this one.

Related ports

The same software or family in MidnightBSD: one homepage, or one name but for a version or a variant.

Configuration

Options name: ai_ollama

OptionDefaultDescription
CPUonBuild CPU backend shared libraries for various SIMD instruction sets
MLXonBuild MLX backend for image generation (CPU)
VULKANonBuild Vulkan GPU backend shared library
USES
cmake:indirect go:1.26+,modules localbase pkgconfig
Service scripts
ollama

Files

distinfo 8
FileSizeSHA256
go/ai_ollama/ollama-v0.34.3/b10760.tar.gz3.7131759e+078986285d34f7531e84b1ee6d35c88989fc6f3cf895f60610594997b8b7bad443
go/ai_ollama/ollama-v0.34.3/llama-b10760-ui.tar.gz3.08112e+06b7f7d173c0faa6582896d2d23603c1bb2d963eedf8845db0a8399d2c1e0ce360
go/ai_ollama/ollama-v0.34.3/d9add9d11f3154111a4c85f267ec2fd307ecd18e.tar.gz4.438516e+06f3ff5fa6dfe738d7a79663fd7a2815dd558bf521163ba0aa867b77a54b0ed8b3
go/ai_ollama/ollama-v0.34.3/ebc88f10caa1b625e6b581437a8dea6df8a70085.tar.gz1787230559a688fe6ef20f6bcb6aac3b419e878fcbc295e19bef816afd51e4b3134e25
go/ai_ollama/ollama-v0.34.3/json.tar.xz110988d6c65aca6b1ed68e7a182f4757257b107ae403032760ed6ef121c9d55e81757d
go/ai_ollama/ollama-v0.34.3/v0.34.3.mod376348a2032d29197914e0bd6de7adf20b4d37ad2aed5e6adb8199cc91e704a50400
go/ai_ollama/ollama-v0.34.3/v0.34.3.zip2.7674219e+07859247e5a7e16a9abe2981253867efeba4be99077216f0bc56ec8b87d607c17c
go/ai_ollama/ollama-v0.34.3/mlc-ai-xgrammar-v0.2.5_GH0.tar.gz1.071195e+067cf5e69ba0bc2695a9f1a97eeb4cc567aac3d644fd329e7d8072ab6f3517b777
Master sites 2
  • https://github.com/ggml-org/llama.cpp/archive/refs/tags/:llamasrc
  • https://github.com/ggml-org/llama.cpp/releases/download/b10760/:llamasrc

Commit history 5

DateCommitCreditsLog message
3bb1790d8a Lucas Holt ai/ollama: update to 0.34.3 (#1763)
e7b96113b0 Lucas Holt devel/libfmt: update to 12.1.0 and fix the tree for fmt 12 (#853)
Updates `devel/libfmt` from 9.1.0 to 12.1.0 and fixes every consumer that breaks as a result. Originally a prerequisite for `ai/pytorch` 2.13.0 (#851), which vendors fmt 12.1.0 and does not build against fmt 9. > **This must land as a single unit.** Between libfmt 12 going in and the > consumers being rebuilt, a stale consumer breaks *unrelated* builds with > misleading errors — a leftover `libze_loader.so.1` needing `libfmt.so.9` > made `net/openmpi4`'s configure report a bogus "cannot link hwloc". The > builder should rebuild all 26 touched ports. ## Core | Port | Change | |---|---| | `devel/libfmt` | 9.1.0 → 12.1.0 (SONAME `.so.9` → `.so.12`) | | `devel/spdlog` | 1.15.0 → 1.17.0 — 1.15 doesn't compile against fmt 12 …
e5ad6a38cf Lucas Holt ai/ollama: fix install
bfe9c30492 Lucas Holt ai/ollama: fix category move staging
AI-Assisted-by: OpenAI Codex <[email protected]> Signed-off-by: Lucas Holt <[email protected]>
dee1e47e52 Lucas Holt ai: add new category and move AI/ML ports from misc
Create the ai category (Artificial intelligence and machine learning) and relocate 42 AI/ML ports from misc into it. - Register ai in Mk/bsd.mport.mk VALID_CATEGORIES and the top-level Makefile - Add ai/Makefile; drop the moved entries from misc/Makefile (also removes the stale linux-claude SUBDIR left over from the claude-code rename) - git mv 42 ports and set their primary CATEGORIES to ai - Rewrite misc/<port> dependency origins to ai/<port> in external dependents (devel/py-beartype, math/py-faiss, multimedia/py-torchcodec, textproc/py-tokenizers) and among the moved ports themselves - Record the origin migrations in MOVED Ports moved: chatgpt-shell-cli, claude-code, claude-code-legacy, clawhub, codex, gemini-cli, github-copilot-cli, grok-cli, lean-ctx, llama-cpp, ollama, …