github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3976] Slow downloads #80140

New Issue
Open
opened 2026-05-09 08:18:20 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-05-09 08:18:20 -05:00
Owner
Copy Link

Originally created by @Alchemistqqqq on GitHub (Apr 27, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3976

What is the issue?

curl -fsSL https://ollama.com/install.sh | sh
After running this one-click download, the download is slow and the connection is disconnected
User
(base) h3c@h3c-UniServer-R4900-G3:/$ curl -fsSL https://ollama.com/install.sh | sh

Downloading ollama...
######################################################################## 100.0%##O#-# ############ 17.3%curl: (18) HTTP/2 stream 1 was reset
Next, I tried the manual installation from the tutorial
sudo curl -L https://ollama.com/download/ollama-linux-amd64 -o /usr/bin/ollama
This command is still slow to download.So I chose to download it locally and drag it into the appropriate folder on my server. Then I followed the tutorial all the way to running the following command
sudo systemctl start ollama
image
(base) h3c@h3c-UniServer-R4900-G3:/$ nvidia-smi
Sat Apr 27 16:58:52 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.171.04 Driver Version: 535.171.04 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Tesla T4 Off | 00000000:18:00.0 Off | Off |
| N/A 38C P8 9W / 70W | 7MiB / 16384MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 1 Tesla T4 Off | 00000000:AF:00.0 Off | Off |
| N/A 36C P8 9W / 70W | 7MiB / 16384MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 1645 G /usr/lib/xorg/Xorg 4MiB |
| 1 N/A N/A 1645 G /usr/lib/xorg/Xorg 4MiB |
+---------------------------------------------------------------------------------------+
The above is my gpu information. Could you please provide me with some help? Thank you

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.1.32

Originally created by @Alchemistqqqq on GitHub (Apr 27, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3976 ### What is the issue? curl -fsSL https://ollama.com/install.sh | sh After running this one-click download, the download is slow and the connection is disconnected User (base) h3c@h3c-UniServer-R4900-G3:/$ curl -fsSL https://ollama.com/install.sh | sh >>> Downloading ollama... ######################################################################## 100.0%##O#-# ############ 17.3%curl: (18) HTTP/2 stream 1 was reset Next, I tried the manual installation from the tutorial sudo curl -L https://ollama.com/download/ollama-linux-amd64 -o /usr/bin/ollama This command is still slow to download.So I chose to download it locally and drag it into the appropriate folder on my server. Then I followed the tutorial all the way to running the following command sudo systemctl start ollama ![image](https://github.com/ollama/ollama/assets/146717415/f41bf83d-1c10-4bc3-9b4e-25f4c6796244) (base) h3c@h3c-UniServer-R4900-G3:/$ nvidia-smi Sat Apr 27 16:58:52 2024 +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.171.04 Driver Version: 535.171.04 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 Tesla T4 Off | 00000000:18:00.0 Off | Off | | N/A 38C P8 9W / 70W | 7MiB / 16384MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ | 1 Tesla T4 Off | 00000000:AF:00.0 Off | Off | | N/A 36C P8 9W / 70W | 7MiB / 16384MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ +---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | 0 N/A N/A 1645 G /usr/lib/xorg/Xorg 4MiB | | 1 N/A N/A 1645 G /usr/lib/xorg/Xorg 4MiB | +---------------------------------------------------------------------------------------+ The above is my gpu information. Could you please provide me with some help? Thank you ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.32
GiteaMirror added the registryfeedback wantedbug labels 2026-05-09 08:18:20 -05:00
GiteaMirror commented 2026-05-09 08:18:22 -05:00
Author
Owner
Copy Link

@helium729 commented on GitHub (Apr 28, 2024):

You'd better use proxy in mainland, China to download github resources

<!-- gh-comment-id:2081509787 --> @helium729 commented on GitHub (Apr 28, 2024): You'd better use proxy in mainland, China to download github resources
GiteaMirror commented 2026-05-09 08:18:22 -05:00
Author
Owner
Copy Link

@GreatBigWhiteWorld commented on GitHub (Apr 29, 2024):

Docker的代理设置要在配置文件里专门设置否则直连
参考https://docs.docker.com/reference/cli/dockerd/#proxy-configuration

<!-- gh-comment-id:2081766519 --> @GreatBigWhiteWorld commented on GitHub (Apr 29, 2024): Docker的代理设置要在配置文件里专门设置否则直连 参考https://docs.docker.com/reference/cli/dockerd/#proxy-configuration
GiteaMirror commented 2026-05-09 08:18:22 -05:00
Author
Owner
Copy Link

@Alchemistqqqq commented on GitHub (Apr 29, 2024):

Docker的代理设置要在配置文件里专门设置否则直连 参考 https://docs.docker.com/reference/cli/dockerd/#proxy-configuration

Thanks, but I forgot to try docker. Maybe I should try it now.

<!-- gh-comment-id:2081771027 --> @Alchemistqqqq commented on GitHub (Apr 29, 2024): > Docker的代理设置要在配置文件里专门设置否则直连 参考 https://docs.docker.com/reference/cli/dockerd/#proxy-configuration Thanks, but I forgot to try docker. Maybe I should try it now.
GiteaMirror commented 2026-05-09 08:18:23 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Apr 30, 2024):

Ollama 在中国还没有镜像。 可以问一下在国内有没有被封？ 现在是在cloudflare 上

<!-- gh-comment-id:2087027601 --> @mchiang0610 commented on GitHub (Apr 30, 2024): Ollama 在中国还没有镜像。 可以问一下在国内有没有被封？ 现在是在cloudflare 上
GiteaMirror commented 2026-05-09 08:18:24 -05:00
Author
Owner
Copy Link

@Alchemistqqqq commented on GitHub (May 8, 2024):

Ollama 在中国还没有镜像。可以问一下在国内有没有被封吗？现在在cloudflare 上

I can't find relevant content, could you please provide me with this website? Thank you.

<!-- gh-comment-id:2099988001 --> @Alchemistqqqq commented on GitHub (May 8, 2024): > Ollama 在中国还没有镜像。可以问一下在国内有没有被封吗？现在在cloudflare 上 I can't find relevant content, could you please provide me with this website? Thank you.
GiteaMirror commented 2026-05-09 08:18:24 -05:00
Author
Owner
Copy Link

@Ltyro commented on GitHub (Jul 25, 2024):

windows下，ollama pull怎么加代理

<!-- gh-comment-id:2249257793 --> @Ltyro commented on GitHub (Jul 25, 2024): windows下，ollama pull怎么加代理
GiteaMirror commented 2026-05-09 08:18:25 -05:00
Author
Owner
Copy Link

@typ431127 commented on GitHub (Aug 9, 2024):

ollama 中国可用镜像源 https://docker.aityp.com/r/docker.io/ollama/ollama

<!-- gh-comment-id:2277017292 --> @typ431127 commented on GitHub (Aug 9, 2024): ollama 中国可用镜像源 https://docker.aityp.com/r/docker.io/ollama/ollama
GiteaMirror commented 2026-05-09 08:18:25 -05:00
Author
Owner
Copy Link

@Abhishek21k commented on GitHub (Jan 21, 2025):

still facing this issue

<!-- gh-comment-id:2605582844 --> @Abhishek21k commented on GitHub (Jan 21, 2025): still facing this issue
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug feedback wanted registry
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#80140
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?