github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8856] Unable to finish download #67797

New Issue
Closed
opened 2026-05-04 11:43:30 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-05-04 11:43:30 -05:00
Owner
Copy Link

Originally created by @gs-rumana on GitHub (Feb 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8856

What is the issue?

I was downloading the DeepSeek-R1 (70b) model, and my download was going backwards. For example, if the download reaches 500MB, it will go to 450MB and then go above 500MB.
Here's a Video for this behavior

https://github.com/user-attachments/assets/6dcdd5f4-9e0b-49e4-a5af-86f70341bb68

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.5.7

Originally created by @gs-rumana on GitHub (Feb 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8856 ### What is the issue? I was downloading the DeepSeek-R1 (70b) model, and my download was going backwards. For example, if the download reaches 500MB, it will go to 450MB and then go above 500MB. Here's a Video for this behavior https://github.com/user-attachments/assets/6dcdd5f4-9e0b-49e4-a5af-86f70341bb68 ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.5.7
GiteaMirror added the networkingbug labels 2026-05-04 11:43:30 -05:00
GiteaMirror commented 2026-05-04 11:43:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 5, 2025):

Server logs will aid in debugging, but this likely the stalling problem:https://github.com/ollama/ollama/issues/8632. This script may work on macOS.

<!-- gh-comment-id:2637857474 --> @rick-github commented on GitHub (Feb 5, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging, but this likely the stalling problem:https://github.com/ollama/ollama/issues/8632. [This script](https://github.com/ollama/ollama/issues/8535#issuecomment-2613241807) may work on macOS.
GiteaMirror commented 2026-05-04 11:43:33 -05:00
Author
Owner
Copy Link

@1251801899 commented on GitHub (Feb 6, 2025):

My Windows also encounters this problem. At first, it is fully utilized, and then it approaches zero.

<!-- gh-comment-id:2638684245 --> @1251801899 commented on GitHub (Feb 6, 2025): My Windows also encounters this problem. At first, it is fully utilized, and then it approaches zero.
GiteaMirror commented 2026-05-04 11:43:33 -05:00
Author
Owner
Copy Link

@DreamLuckyStar commented on GitHub (Feb 7, 2025):

我的 Windows 也遇到了这个问题。起初，它被充分利用，然后接近零。

me too

<!-- gh-comment-id:2641742493 --> @DreamLuckyStar commented on GitHub (Feb 7, 2025): > 我的 Windows 也遇到了这个问题。起初，它被充分利用，然后接近零。 me too
GiteaMirror commented 2026-05-04 11:43:34 -05:00
Author
Owner
Copy Link

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

Issue is still there. as soon as the donload size hits about 300MB, the download restarts from the begining. (Trying to download 7b-qwen-distill-q8_0

OLLAMA_VERSION=0.5.7

System Details Report

Report details

  • Date generated: 2025-02-08 23:37:38

Hardware Information:

  • Hardware Model: ASUSTeK COMPUTER INC. ASUS Zenbook S 16 UM5606WA_UM5606WA
  • Memory: 32.0 GiB
  • Processor: AMD Ryzen™ AI 9 HX 370 w/ Radeon™ 890M × 24
  • Graphics: AMD Radeon™ Graphics
  • Disk Capacity: 1.0 TB

Software Information:

  • Firmware Version: UM5606WA.316
  • OS Name: Ubuntu 24.10
  • OS Build: (null)
  • OS Type: 64-bit
  • GNOME Version: 47
  • Windowing System: Wayland
  • Kernel Version: Linux 6.11.0-14-generic
<!-- gh-comment-id:2645887827 --> @hashangit commented on GitHub (Feb 8, 2025): Issue is still there. as soon as the donload size hits about 300MB, the download restarts from the begining. (Trying to download [7b-qwen-distill-q8_0](https://ollama.com/library/deepseek-r1:7b-qwen-distill-q8_0) OLLAMA_VERSION=0.5.7 # System Details Report --- ## Report details - **Date generated:** 2025-02-08 23:37:38 ## Hardware Information: - **Hardware Model:** ASUSTeK COMPUTER INC. ASUS Zenbook S 16 UM5606WA_UM5606WA - **Memory:** 32.0 GiB - **Processor:** AMD Ryzen™ AI 9 HX 370 w/ Radeon™ 890M × 24 - **Graphics:** AMD Radeon™ Graphics - **Disk Capacity:** 1.0 TB ## Software Information: - **Firmware Version:** UM5606WA.316 - **OS Name:** Ubuntu 24.10 - **OS Build:** (null) - **OS Type:** 64-bit - **GNOME Version:** 47 - **Windowing System:** Wayland - **Kernel Version:** Linux 6.11.0-14-generic
GiteaMirror commented 2026-05-04 11:43:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 8, 2025):

There's a fix in 0.5.8. Until then, https://github.com/ollama/ollama/issues/8484#issuecomment-2627410336 or https://github.com/ollama/ollama/issues/8535#issuecomment-2613241807

<!-- gh-comment-id:2645888880 --> @rick-github commented on GitHub (Feb 8, 2025): There's a fix in 0.5.8. Until then, https://github.com/ollama/ollama/issues/8484#issuecomment-2627410336 or https://github.com/ollama/ollama/issues/8535#issuecomment-2613241807
GiteaMirror commented 2026-05-04 11:43:34 -05:00
Author
Owner
Copy Link

@gs-rumana commented on GitHub (Feb 8, 2025):

There's a fix in 0.5.8. Until then, #8484 (comment) or #8535 (comment)

Not worked for me.

<!-- gh-comment-id:2645889965 --> @gs-rumana commented on GitHub (Feb 8, 2025): > There's a fix in 0.5.8. Until then, [#8484 (comment)](https://github.com/ollama/ollama/issues/8484#issuecomment-2627410336) or [#8535 (comment)](https://github.com/ollama/ollama/issues/8535#issuecomment-2613241807) Not worked for me.
GiteaMirror commented 2026-05-04 11:43:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 8, 2025):

Not worked for me.

Details.

<!-- gh-comment-id:2645890268 --> @rick-github commented on GitHub (Feb 8, 2025): > Not worked for me. Details.
GiteaMirror commented 2026-05-04 11:43:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 4, 2025):

The download stalls should be mitigated as of 0.5.8 by #8831 and #9294 provides an overhaul of model pulling, so closing but feel free to add updates if you are still having issues.

<!-- gh-comment-id:2698061145 --> @rick-github commented on GitHub (Mar 4, 2025): The download stalls should be mitigated as of 0.5.8 by #8831 and #9294 provides an overhaul of model pulling, so closing but feel free to add updates if you are still having issues.
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 networking
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#67797
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?