Ollama Files

Get up and running with Llama 2 and other large language models

This is an exact mirror of the Ollama project, hosted at https://github.com/jmorganca/ollama. SourceForge is not affiliated with Ollama. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
Ollama.dmg	2025-12-16	60.1 MB	2
OllamaSetup.exe	2025-12-16	1.3 GB	2
ollama-linux-arm64.tgz	2025-12-16	2.1 GB	0
ollama-linux-arm64-jetpack5.tgz	2025-12-16	475.1 MB	0
ollama-linux-arm64-jetpack6.tgz	2025-12-16	374.9 MB	2
ollama-linux-amd64-rocm.tgz	2025-12-16	1.3 GB	0
ollama-linux-amd64.tgz	2025-12-16	2.0 GB	0
ollama-darwin.tgz	2025-12-16	27.9 MB	0
ollama-windows-arm64.zip	2025-12-16	22.4 MB	0
ollama-windows-amd64.zip	2025-12-16	2.0 GB	0
ollama-windows-amd64-rocm.zip	2025-12-16	376.9 MB	11
Ollama-darwin.zip	2025-12-16	60.0 MB	0
sha256sum.txt	2025-12-16	1.1 kB	0
README.md	2025-12-16	926 Bytes	0
v0.13.4 source code.tar.gz	2025-12-16	20.9 MB	0
v0.13.4 source code.zip	2025-12-16	21.7 MB	0
Totals: 16 Items		10.2 GB	17

New Models

Nemotron 3 Nano: A new Standard for Efficient, Open, and Intelligent Agentic Models
Olmo 3 and Olmo 3.1: A series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

What's Changed

Enable Ollama engine by default for remaining models
Enable Flash Attention automatically for models by default
Fixed handling of long contexts with Gemma 3 models
Fixed issue that would occur with Gemma 3 QAT models or other models imported with the Gemma 3 architecture

New Contributors

@familom made their first contribution in https://github.com/ollama/ollama/pull/13220

Full Changelog: https://github.com/ollama/ollama/compare/v0.13.3...v0.13.4-rc0

Source: README.md, updated 2025-12-16

Other Useful Business Software

Stay in Flow. Let Zenflow Handle the Heavy Lifting. Icon

Stay in Flow. Let Zenflow Handle the Heavy Lifting.

Your AI engineering control center. Zenflow turns specs into shipped features using parallel agents and multi-repo intelligence.

Zenflow is your engineering control center, turning specs into shipped features. Parallel agents handle coding, testing, and refactoring with real repo context. Multi-agent workflows remove bottlenecks and automate routine work so developers stay focused and in flow.

Try free now

Our Free Plans just got better! | Auth0 Icon

Our Free Plans just got better! | Auth0

With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.

Try free now

Recommended Projects

Chinese-LLaMA-Alpaca 2
Chinese LLaMA-2 & Alpaca-2 Large Model Phase II Project
fullmoon
Chat with private and local large language models
llama.cpp
Port of Facebook's LLaMA model in C/C++
LLM CLI
Access large language models from the command-line
GPT4All
Run Local LLMs on Any Device. Open-source