[GH-ISSUE #6782] Windows Portable Mode #66312

New Issue

GiteaMirror · 2026-05-04T02:26:06-05:00

GiteaMirror commented

2026-05-04 02:26:06 -05:00

Originally created by @SmilerRyan on GitHub (Sep 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6782

I would like to see a Full Portable version of Ollama for Windows, not just having the binary files without running the setup.

My proposal is simply to have the same files as the installer version, and also include a portable.txt file to indicate that it is a portable install and to directly save Ollama settings, history, models etc into a data folder inside the portable build instead of AppData and the User Home folder.

For updates clicking the notification can just open the link to the zip file for manual installation/updates or automatically download and on click open in the default zip program.

Originally created by @SmilerRyan on GitHub (Sep 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6782 I would like to see a Full Portable version of Ollama for Windows, not just having the binary files without running the setup. My proposal is simply to have the same files as the installer version, and also include a portable.txt file to indicate that it is a portable install and to directly save Ollama settings, history, models etc into a data folder inside the portable build instead of AppData and the User Home folder. For updates clicking the notification can just open the link to the zip file for manual installation/updates or automatically download and on click open in the default zip program.

GiteaMirror added the feature request label 2026-05-04 02:26:06 -05:00

GiteaMirror commented

2026-05-04 02:26:14 -05:00

@TangentFoxy commented on GitHub (Nov 1, 2024):

Wait, there's a way to get the binaries without the installer? How do I do that? The installer just fucked me over by choosing a full drive automatically to try to install to.

@TangentFoxy commented on GitHub (Nov 1, 2024): Wait, there's a way to get the binaries without the installer? How do I do that? The installer just fucked me over by choosing a full drive automatically to try to install to.

GiteaMirror commented

2026-05-04 02:26:20 -05:00

@SmilerRyan commented on GitHub (Nov 1, 2024):

I use a tool called Universal Extractor, in the backend it has many different tools for extracting all types of installers.

Though this issue I'm hoping they implement a zip download so these extractors are not needed and so it can actually be run in a portable manner.

@SmilerRyan commented on GitHub (Nov 1, 2024): I use a tool called Universal Extractor, in the backend it has many different tools for extracting all types of installers. Though this issue I'm hoping they implement a zip download so these extractors are not needed and so it can actually be run in a portable manner.

GiteaMirror commented

2026-05-04 02:26:25 -05:00

@smarthiesbs commented on GitHub (Nov 17, 2024):

I would also like to use Ollama "portable", i.e. make it available in a folder without installation.

The reason for this is that I have local admin rights at work (so I could install it normally), but the central IT doesn't like this and there is always the risk that they will remove unapproved programs without asking (to prevent evil "shadow IT"). From an IT security point of view, this is understandable. However, my job is also to advance our department technically, and I need an appropriate environment for testing.

So I'd prefer to bundle Ollama with OpenWebUI, so it's all 'self-contained' and all dependencies are fullfilled in that one folder.

My approach would be to copy the Ollama binaries (C:\Users[User]\AppData\Local\Programs\Ollama) from my private installation into such a folder and set all paths and environment variables with a Powershell startup script. For OpenWebUI I would use a portable Python installation. I realize that this makes updating more difficult, but I can live with that.

Does this work? Has anyone done this or something similar? Is there anything I need to take into account?

@smarthiesbs commented on GitHub (Nov 17, 2024): I would also like to use Ollama "portable", i.e. make it available in a folder without installation. The reason for this is that I have local admin rights at work (so I could install it normally), but the central IT doesn't like this and there is always the risk that they will remove unapproved programs without asking (to prevent evil "shadow IT"). From an IT security point of view, this is understandable. However, my job is also to advance our department technically, and I need an appropriate environment for testing. So I'd prefer to bundle Ollama with OpenWebUI, so it's all 'self-contained' and all dependencies are fullfilled in that one folder. My approach would be to copy the Ollama binaries (C:\Users\[User]\AppData\Local\Programs\Ollama\) from my private installation into such a folder and set all paths and environment variables with a Powershell startup script. For OpenWebUI I would use a portable Python installation. I realize that this makes updating more difficult, but I can live with that. Does this work? Has anyone done this or something similar? Is there anything I need to take into account?

GiteaMirror commented

2026-05-04 02:26:28 -05:00

@SmilerRyan commented on GitHub (Nov 17, 2024):

So I'd prefer to bundle Ollama with OpenWebUI, so it's all 'self-contained' and all dependencies are fullfilled in that one folder.

I've used portable python before, not specifically with OpenWebUI but it should work.

Has anyone done this or something similar? Is there anything I need to take into account?

Currently ollama with the extracted binaries work well, just make sure to always run it from this batch file:

@echo off
title Ollama Portable
set OLLAMA_ORIGINS=*
set OLLAMA_HOST=0.0.0.0
set userprofile=%cd%\data
set localappdata=%cd%\data\AppData\Local
cmd /k ollama.exe

Only downside currently is if there is an update it will download it and update over the "virtual" appdata, so you'll need to manually move the files over the original to apply the update, and manually delete the installation it puts into the registry to uninstall it.

I'm hoping a commit is pushed one day where i can set OLLAMA_UPDATECHECKER to false or similar, or even better an overall portable version that doesent use the registry.

@SmilerRyan commented on GitHub (Nov 17, 2024): > So I'd prefer to bundle Ollama with OpenWebUI, so it's all 'self-contained' and all dependencies are fullfilled in that one folder. I've used portable python before, not specifically with OpenWebUI but it should work. > Has anyone done this or something similar? Is there anything I need to take into account? Currently ollama with the extracted binaries work well, just make sure to always run it from this batch file: ``` @echo off title Ollama Portable set OLLAMA_ORIGINS=* set OLLAMA_HOST=0.0.0.0 set userprofile=%cd%\data set localappdata=%cd%\data\AppData\Local cmd /k ollama.exe ``` Only downside currently is if there is an update it will download it and update over the "virtual" appdata, so you'll need to manually move the files over the original to apply the update, and manually delete the installation it puts into the registry to uninstall it. I'm hoping a commit is pushed one day where i can set `OLLAMA_UPDATECHECKER` to false or similar, or even better an overall portable version that doesent use the registry.

GiteaMirror commented

2026-05-04 02:26:34 -05:00

@smarthiesbs commented on GitHub (Nov 17, 2024):

Thanks a lot for your quick response and the additional details. Then I'll give it a try :)

I'm certainly hoping for an official portable version of ollama as well, which would then require less configuration work and enable a better update process...

@smarthiesbs commented on GitHub (Nov 17, 2024): Thanks a lot for your quick response and the additional details. Then I'll give it a try :) I'm certainly hoping for an official portable version of ollama as well, which would then require less configuration work and enable a better update process...

GiteaMirror commented

2026-05-04 02:26:37 -05:00

@feO2x commented on GitHub (Nov 25, 2024):

I'd like to second that. Ollama in portable mode would help all those Windows users which have to work on computers locked down by their IT department.

@feO2x commented on GitHub (Nov 25, 2024): I'd like to second that. Ollama in portable mode would help all those Windows users which have to work on computers locked down by their IT department.

GiteaMirror commented

2026-05-04 02:26:42 -05:00

@laurenceanthony commented on GitHub (Dec 27, 2024):

I would like a portable version, too.

@laurenceanthony commented on GitHub (Dec 27, 2024): I would like a portable version, too.

GiteaMirror commented

2026-05-04 02:26:49 -05:00

@Christoph1987 commented on GitHub (Jan 23, 2025):

In addition to the portable version, it would be good if you could simply specify in the setup that Ollama is installed in Program Files for all users and not in the user directory. All data should also be saved in Program Files or ProgramData and not in the user directory.

@Christoph1987 commented on GitHub (Jan 23, 2025): In addition to the portable version, it would be good if you could simply specify in the setup that Ollama is installed in Program Files for all users and not in the user directory. All data should also be saved in Program Files or ProgramData and not in the user directory.

GiteaMirror commented

2026-05-04 02:26:55 -05:00

@BobFreqMob commented on GitHub (Jan 23, 2025):

Hi there, my request is almost the same like the others here: i would like an option to choose the installation folder when installing in windows

@BobFreqMob commented on GitHub (Jan 23, 2025): Hi there, my request is almost the same like the others here: i would like an option to choose the installation folder when installing in windows

GiteaMirror commented

2026-05-04 02:27:01 -05:00

@ZhianLin commented on GitHub (Jan 29, 2025):

use in one file，perhaps llamafile，usage https://developer.aliyun.com/article/1434175
或许可以使用 llamafile，使用方法 https://developer.aliyun.com/article/1434175

@ZhianLin commented on GitHub (Jan 29, 2025): use in one file，perhaps [llamafile](https://github.com/Mozilla-Ocho/llamafile)，usage https://developer.aliyun.com/article/1434175 或许可以使用 [llamafile](https://github.com/Mozilla-Ocho/llamafile)，使用方法 https://developer.aliyun.com/article/1434175

GiteaMirror commented

2026-05-04 02:27:07 -05:00

@dexterhuh commented on GitHub (Feb 11, 2025):

I would love to have a portable version on Windows, so I can package Ollama with my Python script together for my end user, and then my end user can use Ollama directly without installing/configuring it. Has anyone figured out a way for the portable mode on Windows?

@dexterhuh commented on GitHub (Feb 11, 2025): I would love to have a portable version on Windows, so I can package Ollama with my Python script together for my end user, and then my end user can use Ollama directly without installing/configuring it. Has anyone figured out a way for the portable mode on Windows?

GiteaMirror commented

2026-05-04 02:27:10 -05:00

@SmilerRyan commented on GitHub (Feb 11, 2025):

For using it portably using a batch file yes, but disabling the updater so it doesn't attempt to reinstall itself no.

@SmilerRyan commented on GitHub (Feb 11, 2025): For using it portably using a batch file yes, but disabling the updater so it doesn't attempt to reinstall itself no.

GiteaMirror commented

2026-05-04 02:27:15 -05:00

@dexterhuh commented on GitHub (Feb 11, 2025):

For using it portably using a batch file yes, but disabling the updater so it doesn't attempt to reinstall itself no.

Thank you for the information. I'm a beginner. Do you know if there is a guide page for doing that?

@dexterhuh commented on GitHub (Feb 11, 2025): > For using it portably using a batch file yes, but disabling the updater so it doesn't attempt to reinstall itself no. Thank you for the information. I'm a beginner. Do you know if there is a guide page for doing that?

GiteaMirror commented

2026-05-04 02:27:22 -05:00

@foss-lover34 commented on GitHub (Feb 20, 2025):

hey @SmilerRyan you sound like an advanced user, could you help me setting up a portable version of ollama please, i didnt quite get it

@foss-lover34 commented on GitHub (Feb 20, 2025): hey @SmilerRyan you sound like an advanced user, could you help me setting up a portable version of ollama please, i didnt quite get it

GiteaMirror commented

2026-05-04 02:27:27 -05:00

@SmilerRyan commented on GitHub (Feb 27, 2025):

hey @SmilerRyan you sound like an advanced user, could you help me setting up a portable version of ollama please, i didnt quite get it

Sure, basically:

Download the Ollama Files.
Install the full version using the exe, copy the files it installs, then uninstall it.
Using this makes sure it has all the files it needs (the zips don't have everything required).

I've just tried myself with the zip method, the files that are missing are:

"ollama app.exe"
"app.ico"
"ollama_welcome.ps1"

The .ico and .ps1 file aren't nessacary but nowdays it seems Ollama can't run without the app file.

Move your Ollama files into a folder of your choice.
You can put your files wherever you want, with write permissions.
eg. C:\OllamaPortable\ or C:\Users\Ryan\Documents\OllamaPortable\
Create the Ollama Portable Launcher.
Open Notepad, and write the following code (copy and paste).
Save this file as OllamaPortable.bat into your OllamaPortable folder.

@echo off
title Ollama Portable
set OLLAMA_ORIGINS=*
set OLLAMA_HOST=0.0.0.0
set userprofile=%cd%\data
set localappdata=%cd%\data\AppData\Local
cmd /k ollama.exe

Open Ollama and download/run/test models etc.
Every time you want to run ollama, you can now run the OllamaPortable.bat file.

It sets the variables to make the thing run portably, as well as allows the Ollama server to listen on any IP and accept any connection for websites.

Usage for other UIs and tools etc.

Assuming you already have done an ollama pull or ollama run before in this instance (the same as regular ollama to get a model), you can serve it by running ollama serve for use in other applications/uis etc.

You can also edit or make a second batch file called OllamaPortableServe.bat if you want to make a quick serve version, just add this line to the end of the file:

cmd /k ollama.exe serve

Updating etc

As for updating, if it asks and goes through, it'll go into the AppData folder in your portable folder. Once it's done you can move all of the files out into the main OllamaPortable folder, replacing the existing ones, and then restart Ollama. If you don't do this and just re-run it, then you'll always be using the same old version since it's not running the latest one.

After moving it, to completely clean up the installation, go to your installed programs list (appwiz.cpl) and select to "uninstall" Ollama, it will fail and say the file does not exist. Click yes to remove it from there, and you're done.

@SmilerRyan commented on GitHub (Feb 27, 2025): > hey [@SmilerRyan](https://github.com/SmilerRyan) you sound like an advanced user, could you help me setting up a portable version of ollama please, i didnt quite get it Sure, basically: 1. Download the Ollama Files. Install the full version using the exe, copy the files it installs, then uninstall it. Using this makes sure it has all the files it needs (the zips don't have everything required). I've just tried myself with the zip method, the files that are missing are: - "ollama app.exe" - "app.ico" - "ollama_welcome.ps1" The .ico and .ps1 file aren't nessacary but nowdays it seems Ollama can't run without the app file. 2. Move your Ollama files into a folder of your choice. You can put your files wherever you want, with write permissions. eg. C:\OllamaPortable\ or C:\Users\Ryan\Documents\OllamaPortable\ 3. Create the Ollama Portable Launcher. Open Notepad, and write the following code (copy and paste). Save this file as ``OllamaPortable.bat`` into your OllamaPortable folder. ```bat @echo off title Ollama Portable set OLLAMA_ORIGINS=* set OLLAMA_HOST=0.0.0.0 set userprofile=%cd%\data set localappdata=%cd%\data\AppData\Local cmd /k ollama.exe ``` 4. Open Ollama and download/run/test models etc. Every time you want to run ollama, you can now run the ``OllamaPortable.bat`` file. It sets the variables to make the thing run portably, as well as allows the Ollama server to listen on any IP and accept any connection for websites. 5. Usage for other UIs and tools etc. Assuming you already have done an ``ollama pull`` or ``ollama run`` before in this instance (the same as regular ollama to get a model), you can serve it by running ``ollama serve`` for use in other applications/uis etc. You can also edit or make a second batch file called ``OllamaPortableServe.bat`` if you want to make a quick serve version, just add this line to the end of the file: ```bat cmd /k ollama.exe serve ``` 7. Updating etc As for updating, if it asks and goes through, it'll go into the AppData folder in your portable folder. Once it's done you can move all of the files out into the main OllamaPortable folder, replacing the existing ones, and then restart Ollama. If you don't do this and just re-run it, then you'll always be using the same old version since it's not running the latest one. After moving it, to completely clean up the installation, go to your installed programs list (appwiz.cpl) and select to "uninstall" Ollama, it will fail and say the file does not exist. Click yes to remove it from there, and you're done.

GiteaMirror commented

2026-05-04 02:27:32 -05:00

@SmilerRyan commented on GitHub (Mar 5, 2025):

Quick update for "Ollama Portable" you can actually disable the update checker by deleting/renaming the "ollama app.exe" file, and to make the thing work you can just call the "ollama server" command yourself, which is actually all the app does in the background, along with an update checker and tray icon.

Download and unpack Ollama.

Use both zipped files and extract them
Unpack the setup.exe and delete the uninstaller.

Delete, rename or move the "ollama app.exe" file.

I renamed it to "ollama app.exe.disabled" to keep it simple.

Create your "Ollama Portable Launcher" batch file.

@echo off
title Ollama Portable
set OLLAMA_ORIGINS=*
set OLLAMA_HOST=0.0.0.0
set userprofile=%cd%\data
start /b "" ollama.exe serve
timeout 1 > nul
cmd /k ollama.exe

Launch ollama from this file, and enjoy it.

@SmilerRyan commented on GitHub (Mar 5, 2025): Quick update for "Ollama Portable" you can actually disable the update checker by deleting/renaming the "ollama app.exe" file, and to make the thing work you can just call the "ollama server" command yourself, which is actually all the app does in the background, along with an update checker and tray icon. 1. Download and unpack Ollama. - Use both zipped files and extract them - Unpack the setup.exe and delete the uninstaller. 2. Delete, rename or move the "ollama app.exe" file. - I renamed it to "ollama app.exe.disabled" to keep it simple. 3. Create your "Ollama Portable Launcher" batch file. ``` @echo off title Ollama Portable set OLLAMA_ORIGINS=* set OLLAMA_HOST=0.0.0.0 set userprofile=%cd%\data start /b "" ollama.exe serve timeout 1 > nul cmd /k ollama.exe ``` 4. Launch ollama from this file, and enjoy it.

GiteaMirror commented

2026-05-04 02:27:40 -05:00

@hellomynameisnone commented on GitHub (Dec 10, 2025):

Self contained portable batch

1- Copy/paste and name it : "OllamaPortableGUI.bat"

@echo off
title Ollama Portable

:: Stable base path (folder where the .bat is located)
set "BASE=%~dp0"
set "PORTABLE=%BASE%data"


:: Create portable structure if it doesn't exist
if not exist "%PORTABLE%\AppData\Local" mkdir "%PORTABLE%\AppData\Local"
if not exist "%PORTABLE%\AppData\Roaming" mkdir "%PORTABLE%\AppData\Roaming"

:: Redirect users
set "LOCALAPPDATA=%PORTABLE%\AppData\Local"
set "APPDATA=%PORTABLE%\AppData\Roaming"
set "USERPROFILE=%PORTABLE%"

echo Starting Ollama server...

:: Prevent double instance
tasklist | find /i "ollama.exe" >nul
if not errorlevel 1 (
    echo Ollama server already running.
) else (
    start "" "%PORTABLE%\AppData\Local\Programs\Ollama\ollama.exe" serve
)

echo Starting GUI...
start "" "%PORTABLE%\AppData\Local\Programs\Ollama\ollama app.exe"

2 - Create this folder structure:

OllamaPortable/
├─ data/
│  ├─ .ollama/
│  │    └─ models/
│  ├─ AppData/
│  │  ├─ Local/
│  │  │    └─ Programs
│  │  │          └─ Ollama
│  │  │                 └─ lib
│  │  └─ Roaming/
│  └─ Desktop/
└─ OllamaPortableGUI.bat

3 - Download the latest ollama-windows-amd64.zip release

4 - Open zip file and extract "ollama.exe" and "lib" folder in:
X:...\OllamaPortable\data\AppData\Local\Programs\Ollama

NOTE: "ollama app.exe" is not present in the .zip version, to be able to use the Ollama builtin chat, you should install it with the "OllamaSetup.exe" and move/copy the folder structure

@hellomynameisnone commented on GitHub (Dec 10, 2025): Self contained portable batch 1- Copy/paste and name it : "OllamaPortableGUI.bat" ``` @echo off title Ollama Portable :: Stable base path (folder where the .bat is located) set "BASE=%~dp0" set "PORTABLE=%BASE%data" :: Create portable structure if it doesn't exist if not exist "%PORTABLE%\AppData\Local" mkdir "%PORTABLE%\AppData\Local" if not exist "%PORTABLE%\AppData\Roaming" mkdir "%PORTABLE%\AppData\Roaming" :: Redirect users set "LOCALAPPDATA=%PORTABLE%\AppData\Local" set "APPDATA=%PORTABLE%\AppData\Roaming" set "USERPROFILE=%PORTABLE%" echo Starting Ollama server... :: Prevent double instance tasklist | find /i "ollama.exe" >nul if not errorlevel 1 ( echo Ollama server already running. ) else ( start "" "%PORTABLE%\AppData\Local\Programs\Ollama\ollama.exe" serve ) echo Starting GUI... start "" "%PORTABLE%\AppData\Local\Programs\Ollama\ollama app.exe" ``` 2 - Create this folder structure: ``` OllamaPortable/ ├─ data/ │ ├─ .ollama/ │ │ └─ models/ │ ├─ AppData/ │ │ ├─ Local/ │ │ │ └─ Programs │ │ │ └─ Ollama │ │ │ └─ lib │ │ └─ Roaming/ │ └─ Desktop/ └─ OllamaPortableGUI.bat ``` 3 - Download the latest _ollama-windows-amd64.zip_ [release]( https://github.com/ollama/ollama/releases ) 4 - Open zip file and extract "ollama.exe" and "lib" folder in: X:\...\OllamaPortable\data\AppData\Local\Programs\Ollama NOTE: "ollama app.exe" is not present in the .zip version, to be able to use the Ollama builtin chat, you should install it with the "OllamaSetup.exe" and move/copy the folder structure

Sign in to join this conversation.

Branches Tags

main

hoyyeva/anthropic-local-image-path

dhiltgen/ci

dhiltgen/llama-runner

parth-remove-claude-desktop-launch

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#66312