[GH-ISSUE #3794] 模型下载最后1%速度骤降，导致下载时间超长。The download speed suddenly drops at the last 1%, resulting in an extremely long download time. #48853

New Issue

GiteaMirror · 2026-04-28T09:53:12-05:00

GiteaMirror commented

2026-04-28 09:53:12 -05:00

Originally created by @aohanhongzhi on GitHub (Apr 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3794

What is the issue?

模型无论大小，每次下载前面99%都最大的速度可以达到29MB/s。但是最后1%速度就只有几百 KB/s。很奇怪。是进度条有问题，还是啥bug？这在我本地电脑和线上服务器都出现了。

Regardless of model size, in most cases, the download speed reaches 29MB/s for about 99% of the time before completion. However, the last 1% takes only a few hundred KB/s. This is quite strange. Is it an issue with the progress bar or some bug? This phenomenon has been observed on both my local computer and online server.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.32

Originally created by @aohanhongzhi on GitHub (Apr 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3794 ### What is the issue? 模型无论大小，每次下载前面99%都最大的速度可以达到29MB/s。但是最后1%速度就只有几百 KB/s。很奇怪。是进度条有问题，还是啥bug？这在我本地电脑和线上服务器都出现了。 Regardless of model size, in most cases, the download speed reaches 29MB/s for about 99% of the time before completion. However, the last 1% takes only a few hundred KB/s. This is quite strange. Is it an issue with the progress bar or some bug? This phenomenon has been observed on both my local computer and online server. ![image](https://github.com/ollama/ollama/assets/37319319/be1b24f1-922c-4478-8548-74704686e573) ![image](https://github.com/ollama/ollama/assets/37319319/9a8b4e0c-4dc6-4156-bd46-744befb3795e) ![image](https://github.com/ollama/ollama/assets/37319319/87782acf-2caa-40d5-a84a-b19eab38333e) ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.32

GiteaMirror added the bug label 2026-04-28 09:53:12 -05:00

GiteaMirror closed this issue

2026-04-28 09:53:13 -05:00

GiteaMirror commented

2026-04-28 09:53:15 -05:00

@mili-tan commented on GitHub (Apr 21, 2024):

你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。

You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time.

或者你在中国大陆，也可以试试看这个：
https://github.com/onllama/Onllama.ModelScope2Registry

@mili-tan commented on GitHub (Apr 21, 2024): 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 或者你在中国大陆，也可以试试看这个： https://github.com/onllama/Onllama.ModelScope2Registry

GiteaMirror commented

2026-04-28 09:53:16 -05:00

@catundchat commented on GitHub (Apr 22, 2024):

Similar situation on Win10

@catundchat commented on GitHub (Apr 22, 2024): Similar situation on Win10

GiteaMirror commented

2026-04-28 09:53:18 -05:00

@Shzyhao commented on GitHub (Apr 22, 2024):

一样，我是一段时间速度很快，50M/s，但是过了一段时间就很慢，200k/s，问题是没做过变更操作，下qwen二十秒就下完了，下到llama3的时候前面很快，后面就老是报TLS handshake timeout，感觉看脸

@Shzyhao commented on GitHub (Apr 22, 2024): 一样，我是一段时间速度很快，50M/s，但是过了一段时间就很慢，200k/s，问题是没做过变更操作，下qwen二十秒就下完了，下到llama3的时候前面很快，后面就老是报TLS handshake timeout，感觉看脸

GiteaMirror commented

2026-04-28 09:53:23 -05:00

@i-yoyocat commented on GitHub (Apr 24, 2024):

Similar situation on ubuntu22.04

@i-yoyocat commented on GitHub (Apr 24, 2024): Similar situation on ubuntu22.04

GiteaMirror commented

2026-04-28 09:53:27 -05:00

@micsama commented on GitHub (Apr 28, 2024):

similar

@micsama commented on GitHub (Apr 28, 2024): similar

GiteaMirror commented

2026-04-28 09:53:29 -05:00

@pdevine commented on GitHub (Apr 30, 2024):

This is a dupe of #1736

@pdevine commented on GitHub (Apr 30, 2024): This is a dupe of #1736

GiteaMirror commented

2026-04-28 09:53:30 -05:00

@martin-bing commented on GitHub (Aug 5, 2024):

亲测有用，赞！

@martin-bing commented on GitHub (Aug 5, 2024): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 亲测有用，赞！

GiteaMirror commented

2026-04-28 09:53:32 -05:00

@c12h180 commented on GitHub (Sep 3, 2024):

牛逼！

@c12h180 commented on GitHub (Sep 3, 2024): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 牛逼！

GiteaMirror commented

2026-04-28 09:53:34 -05:00

@KK0571 commented on GitHub (Oct 31, 2024):

强制结束有时候会丢进度的，遇到过一次，现在不敢强制取消

@KK0571 commented on GitHub (Oct 31, 2024): 强制结束有时候会丢进度的，遇到过一次，现在不敢强制取消

GiteaMirror commented

2026-04-28 09:53:35 -05:00

@yzwou commented on GitHub (Nov 8, 2024):

富贵险中求吧只能说

@yzwou commented on GitHub (Nov 8, 2024): > 强制结束有时候会丢进度的，遇到过一次，现在不敢强制取消富贵险中求吧只能说

GiteaMirror commented

2026-04-28 09:53:37 -05:00

@franklin520520 commented on GitHub (Nov 14, 2024):

相当好用啊

@franklin520520 commented on GitHub (Nov 14, 2024): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 相当好用啊

GiteaMirror commented

2026-04-28 09:53:38 -05:00

@KK0571 commented on GitHub (Nov 14, 2024):

谢谢，已经尝试过了，有时可以重连高速下载，有时候会连接不上，多尝试几次可以，或者干脆改天pull。

------------------ 原始邮件 ------------------
发件人: @.>;
发送时间: 2024年11月14日(星期四) 上午10:54
收件人: @.>;
抄送: @.>; @.>;
主题: Re: [ollama/ollama] 模型下载最后1%速度骤降，导致下载时间超长。The download speed suddenly drops at the last 1%, resulting in an extremely long download time. (Issue #3794)

你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。

You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time.

相当好用啊

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: @.***>

@KK0571 commented on GitHub (Nov 14, 2024): 谢谢，已经尝试过了，有时可以重连高速下载，有时候会连接不上，多尝试几次可以，或者干脆改天pull。 ------------------ 原始邮件 ------------------ 发件人: ***@***.***>; 发送时间: 2024年11月14日(星期四) 上午10:54 收件人: ***@***.***>; 抄送: ***@***.***>; ***@***.***>; 主题: Re: [ollama/ollama] 模型下载最后1%速度骤降，导致下载时间超长。The download speed suddenly drops at the last 1%, resulting in an extremely long download time. (Issue #3794) 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 相当好用啊 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***>

GiteaMirror commented

2026-04-28 09:53:39 -05:00

@Yu-kio commented on GitHub (Dec 17, 2024):

GREAT

@Yu-kio commented on GitHub (Dec 17, 2024): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. GREAT

GiteaMirror commented

2026-04-28 09:53:41 -05:00

@cryptolimber commented on GitHub (Jan 22, 2025):

you are right！

@cryptolimber commented on GitHub (Jan 22, 2025): you are right！

GiteaMirror commented

2026-04-28 09:53:42 -05:00

@vip91919 commented on GitHub (Jan 23, 2025):

你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。

You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time.
您可以尝试按 Ctrl+C 取消此下载，然后再次重新下载，这不会丢失进度并且可能会更快。这在大多数情况下对我来说都有效。
感谢分享，有效

@vip91919 commented on GitHub (Jan 23, 2025): 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 您可以尝试按 Ctrl+C 取消此下载，然后再次重新下载，这不会丢失进度并且可能会更快。这在大多数情况下对我来说都有效。感谢分享，有效

GiteaMirror commented

2026-04-28 09:53:43 -05:00

@gjnzsu commented on GitHub (Feb 2, 2025):

[下面回复已发现有更快捷的方式]

ctrl+c and resume download
亲测有效，多谢分享

@gjnzsu commented on GitHub (Feb 2, 2025): [下面回复已发现有更快捷的方式] ctrl+c and resume download 亲测有效，多谢分享

GiteaMirror commented

2026-04-28 09:53:44 -05:00

@Peter2555 commented on GitHub (Feb 2, 2025):

没啥作用

@Peter2555 commented on GitHub (Feb 2, 2025): 没啥作用

GiteaMirror commented

2026-04-28 09:53:45 -05:00

@mili-tan commented on GitHub (Feb 2, 2025):

或许，也试试看这个：

https://github.com/onllama/Onllama.ModelScope2Registry

@mili-tan commented on GitHub (Feb 2, 2025): > 没啥作用或许，也试试看这个： https://github.com/onllama/Onllama.ModelScope2Registry

GiteaMirror commented

2026-04-28 09:53:46 -05:00

@siruoqing commented on GitHub (Feb 4, 2025):

Thanks very much

@siruoqing commented on GitHub (Feb 4, 2025): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time.您可以尝试按 Ctrl+C 取消此下载，然后再次重新下载，这不会丢失进度并且可能会更快。这在大多数情况下对我来说都有效。 Thanks very much

GiteaMirror commented

2026-04-28 09:53:48 -05:00

@happyEddiehorse commented on GitHub (Feb 5, 2025):

有用，太棒了！

@happyEddiehorse commented on GitHub (Feb 5, 2025): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 有用，太棒了！

GiteaMirror commented

2026-04-28 09:53:48 -05:00

@likwater commented on GitHub (Feb 6, 2025):

亲测有效，太有用了，感谢感谢

@likwater commented on GitHub (Feb 6, 2025): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 亲测有效，太有用了，感谢感谢

GiteaMirror commented

2026-04-28 09:53:50 -05:00

@James-Xue commented on GitHub (Feb 8, 2025):

牛逼，真的有用！就凭这个评论，我相信AI永远也替代不了网友的评论

@James-Xue commented on GitHub (Feb 8, 2025): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 牛逼，真的有用！就凭这个评论，我相信AI永远也替代不了网友的评论

GiteaMirror commented

2026-04-28 09:53:51 -05:00

@kesshei commented on GitHub (Feb 8, 2025):

重新来一下，确实快很多，感谢！

@kesshei commented on GitHub (Feb 8, 2025): 重新来一下，确实快很多，感谢！

GiteaMirror commented

2026-04-28 09:53:54 -05:00

@seahurt commented on GitHub (Mar 9, 2025):

还是想知道原因

@seahurt commented on GitHub (Mar 9, 2025): 还是想知道原因

GiteaMirror commented

2026-04-28 09:53:58 -05:00

@seeadoog commented on GitHub (Mar 10, 2025):

剩1%时，只有几十kb/s。再到后面只有几kb/s，零点几kb/s 。感觉是故意耍猴呢。

@seeadoog commented on GitHub (Mar 10, 2025): 剩1%时，只有几十kb/s。再到后面只有几kb/s，零点几kb/s 。感觉是故意耍猴呢。

GiteaMirror commented

2026-04-28 09:54:00 -05:00

@mili-tan commented on GitHub (Mar 16, 2025):

这是运营商的 QoS，和 Ollama 无关。还可以试试看修改 Hosts 将 Ollama 的 R2 切换到 Cloudflare 其他节点，然后再重试。

104.18.20.20 registry.ollama.ai
104.18.20.20 dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com

@mili-tan commented on GitHub (Mar 16, 2025): > 剩1%时，只有几十kb/s。再到后面只有几kb/s，零点几kb/s 。感觉是故意耍猴呢。这是运营商的 QoS，和 Ollama 无关。还可以试试看修改 Hosts 将 Ollama 的 R2 切换到 Cloudflare 其他节点，然后再重试。 ``` 104.18.20.20 registry.ollama.ai 104.18.20.20 dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com ```

GiteaMirror commented

2026-04-28 09:54:03 -05:00

@msjsc001 commented on GitHub (Mar 17, 2025):

有用，谢谢！

@msjsc001 commented on GitHub (Mar 17, 2025): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. 有用，谢谢！

GiteaMirror commented

2026-04-28 09:54:06 -05:00

@mkyuangithub commented on GitHub (Apr 27, 2025):

Pls use this script saved as a .ps1 e.g. download_model.ps1 under windows->powershell

run such ps1 under the powershell， it will automaticall restart at 240 seconds and use this to simulate your "ctrl+c and re-pull" behavior.

After test it for several weeks, it never loss download data, enjoy it.

download_model.ps1 script contents:

while ($true) {
$modelExists = ollama list | Select-String "qwen2.5:14b"
if ($modelExists) {
Write-Host "download finish"
break
}
Write-Host "start download..."
$process = Start-Process -FilePath "ollama" -ArgumentList "run", "qwen2.5:14b" -PassThru -NoNewWindow

Start-Sleep -Seconds 240

try {
    Stop-Process -Id $process.Id -Force -ErrorAction Stop
    Write-Host "retry..."
}
catch {
    Write-Host "process finish"
}

}

@mkyuangithub commented on GitHub (Apr 27, 2025): Pls use this script saved as a .ps1 e.g. download_model.ps1 under windows->powershell run such ps1 under the powershell， it will automaticall restart at 240 seconds and use this to simulate your "ctrl+c and re-pull" behavior. After test it for several weeks, it never loss download data, enjoy it. download_model.ps1 script contents: while ($true) { $modelExists = ollama list | Select-String "qwen2.5:14b" if ($modelExists) { Write-Host "download finish" break } Write-Host "start download..." $process = Start-Process -FilePath "ollama" -ArgumentList "run", "qwen2.5:14b" -PassThru -NoNewWindow Start-Sleep -Seconds 240 try { Stop-Process -Id $process.Id -Force -ErrorAction Stop Write-Host "retry..." } catch { Write-Host "process finish" } }

GiteaMirror commented

2026-04-28 09:54:06 -05:00

@mkyuangithub commented on GitHub (Apr 27, 2025):

@mkyuangithub commented on GitHub (Apr 27, 2025): > Pls use this script saved as a .ps1 e.g. download_model.ps1 under windows->powershell > > run such ps1 under the powershell， it will automaticall restart at 240 seconds and use this to simulate your "ctrl+c and re-pull" behavior. > > After test it for several weeks, it never loss download data, enjoy it. > > download_model.ps1 script contents: > > while ($true) { $modelExists = ollama list | Select-String "qwen2.5:14b" if ($modelExists) { Write-Host "download finish" break } Write-Host "start download..." $process = Start-Process -FilePath "ollama" -ArgumentList "run", "qwen2.5:14b" -PassThru -NoNewWindow > > ``` > Start-Sleep -Seconds 240 > > try { > Stop-Process -Id $process.Id -Force -ErrorAction Stop > Write-Host "retry..." > } > catch { > Write-Host "process finish" > } > ``` > > } ![Image](https://github.com/user-attachments/assets/c38c152d-09e0-4764-b5ea-00b691cf9c9d)

GiteaMirror commented

2026-04-28 09:54:07 -05:00

@ShawnBei commented on GitHub (Jun 9, 2025):

有用！感谢

@ShawnBei commented on GitHub (Jun 9, 2025): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. > > 或者你在中国大陆，也可以试试看这个： https://github.com/onllama/Onllama.ModelScope2Registry 有用！感谢

GiteaMirror commented

2026-04-28 09:54:08 -05:00

@Echo-1120 commented on GitHub (Jul 24, 2025):

有用有用！！！太感谢了

@Echo-1120 commented on GitHub (Jul 24, 2025): > > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. > > > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. > > 亲测有用，赞！有用有用！！！太感谢了

GiteaMirror commented

2026-04-28 09:54:10 -05:00

@XiaoPeng0x3 commented on GitHub (Aug 14, 2025):

确实有用，不过很奇怪，哈哈哈

@XiaoPeng0x3 commented on GitHub (Aug 14, 2025): 确实有用，不过很奇怪，哈哈哈

GiteaMirror commented

2026-04-28 09:54:12 -05:00

@qet119 commented on GitHub (Nov 23, 2025):

别信， Ctrl+C 后不会重新续传 👎🏻

@qet119 commented on GitHub (Nov 23, 2025): > 你可以试试看按下 Ctrl+C 取消这次下载，然后再次重新下载，进度不会丢失，速度也许会快很多。这对我绝大多数时间有效。 > > You could try pressing Ctrl+C to cancel this download and then re-download it again, which won't lose progress and might be much faster. This works for me most of the time. > > 或者你在中国大陆，也可以试试看这个： https://github.com/onllama/Onllama.ModelScope2Registry 别信， Ctrl+C 后不会重新续传 👎🏻

GiteaMirror commented

2026-04-28 09:54:13 -05:00

@Javaears commented on GitHub (Feb 13, 2026):

Ctrl+C真的非常好用，多试几次都可以的，可以续传，速度重新上来！

@Javaears commented on GitHub (Feb 13, 2026): Ctrl+C真的非常好用，多试几次都可以的，可以续传，速度重新上来！

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

parth-launch-plan-gating

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#48853