github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6466] I can not push 8g model to Ollama #4068

New Issue
Open
opened 2026-04-12 14:58:32 -05:00 by GiteaMirror · 11 comments
GiteaMirror commented 2026-04-12 14:58:32 -05:00
Owner
Copy Link

Originally created by @hololeo on GitHub (Aug 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6466

What is the issue?

using

ollama push me/mymodel

im getting upload rate like this

39 MB/8.5 GB 1.4 MB/s 1h41m

it will chug chug chug to 40 or 50% then i get the error

Error: max retries exceeded: http status 502 Bad Gateway: <?xml version="1.0" encoding="UTF-8"?>InternalErrorWe encountered an internal connectivity issue. Please try again.

im wondering if my ISP is getting me off? Or perhaps im not uploading fast enough so ollama server cuts me off?

any tips on how to push largish models? it will do 4g ok

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.3.6

Originally created by @hololeo on GitHub (Aug 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6466 ### What is the issue? using >ollama push me/mymodel im getting upload rate like this > 39 MB/8.5 GB 1.4 MB/s 1h41m it will chug chug chug to 40 or 50% then i get the error > Error: max retries exceeded: http status 502 Bad Gateway: <?xml version="1.0" encoding="UTF-8"?><Error><Code>InternalError</Code><Message>We encountered an internal connectivity issue. Please try again.</Message></Error> im wondering if my ISP is getting me off? Or perhaps im not uploading fast enough so ollama server cuts me off? any tips on how to push largish models? it will do 4g ok ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.3.6
GiteaMirror added the bug label 2026-04-12 14:58:32 -05:00
GiteaMirror commented 2026-04-12 14:58:33 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 23, 2024):

Hi @hololeo can you use a website like fast.com to share your download or upload speed? It will help.

<!-- gh-comment-id:2306117761 --> @igorschlum commented on GitHub (Aug 23, 2024): Hi @hololeo can you use a website like fast.com to share your download or upload speed? It will help.
GiteaMirror commented 2026-04-12 14:58:34 -05:00
Author
Owner
Copy Link

@hololeo commented on GitHub (Aug 23, 2024):

thank you for looking into this. screenshot of results

Screenshot 2024-08-23 at 8 20 53 AM

<!-- gh-comment-id:2307309055 --> @hololeo commented on GitHub (Aug 23, 2024): thank you for looking into this. screenshot of results ![Screenshot 2024-08-23 at 8 20 53 AM](https://github.com/user-attachments/assets/44c53546-d621-4845-9051-eaf4cfb09cba)
GiteaMirror commented 2026-04-12 14:58:34 -05:00
Author
Owner
Copy Link

@hololeo commented on GitHub (Sep 1, 2024):

bump? any indication of what I can do on my end to fix this? I suppose moving to better internet but thats difficult and expensive in my locale

<!-- gh-comment-id:2323504012 --> @hololeo commented on GitHub (Sep 1, 2024): bump? any indication of what I can do on my end to fix this? I suppose moving to better internet but thats difficult and expensive in my locale
GiteaMirror commented 2026-04-12 14:58:35 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Sep 2, 2024):

speed

Hi @hololeo, did you try using version 0.3.9? The number of parallel downloads has been adjusted, so it might work better now. If not, I have a bad connection if I use my brother's provider and could try to push a model.

<!-- gh-comment-id:2324060821 --> @igorschlum commented on GitHub (Sep 2, 2024): <img width="687" alt="speed" src="https://github.com/user-attachments/assets/99cc1887-9ede-4987-9043-21195a7d388f"> Hi @hololeo, did you try using version 0.3.9? The number of parallel downloads has been adjusted, so it might work better now. If not, I have a bad connection if I use my brother's provider and could try to push a model.
GiteaMirror commented 2026-04-12 14:58:35 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Sep 2, 2024):

@hololeo as @igorschlum mentioned does the latest version happen to work? If not we will continue improving the networking code to fix this soon – sorry about the issue.

<!-- gh-comment-id:2325288546 --> @jmorganca commented on GitHub (Sep 2, 2024): @hololeo as @igorschlum mentioned does the latest version happen to work? If not we will continue improving the networking code to fix this soon – sorry about the issue.
GiteaMirror commented 2026-04-12 14:58:36 -05:00
Author
Owner
Copy Link

@hololeo commented on GitHub (Sep 5, 2024):

yes i have ollama version 0.3.9. The error still occurs. :(. Thank you for your work and investigating

<!-- gh-comment-id:2330558851 --> @hololeo commented on GitHub (Sep 5, 2024): yes i have ollama version 0.3.9. The error still occurs. :(. Thank you for your work and investigating
GiteaMirror commented 2026-04-12 14:58:36 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Sep 5, 2024):

@hololeo please can you share a screen with the upload ans download speed you get using fast.com?

<!-- gh-comment-id:2330629899 --> @igorschlum commented on GitHub (Sep 5, 2024): @hololeo please can you share a screen with the upload ans download speed you get using fast.com?
GiteaMirror commented 2026-04-12 14:58:36 -05:00
Author
Owner
Copy Link

@purin-blog commented on GitHub (Sep 10, 2024):

PS C:\Users\Admin.ollama\models> ollama create -f Modelfile white_/mario
transferring model data
using existing layer sha256:8de95da68dc485c0889c205384c24642f83ca18d089559c977ffc6a3972a71a8
using existing layer sha256:62fbfd9ed093d6e5ac83190c86eec5369317919f4b149598d2dbb38900e9faef
using existing layer sha256:c156170b718ec29139d3653d40ed1986fd92fb7e0959b5c71f3c48f62e6636f4
creating new layer sha256:b3fb3caebac98f848f5c65ff9eb77c6f3ce8cefd4fad45e94c37725ca847c562
creating new layer sha256:b1c932e03beb32c4ab61bb50b2fa06ab1f2ea4e99ee6495670bbe23834dc7d62
creating new layer sha256:ed36a163da40b1fea25ee506c2b82eb76df4878b4e2afa5db53f42f7a97639e5
writing manifest
success
PS C:\Users\Admin.ollama\models> ollama push white_/mario
retrieving manifest
Error: file does not exist
PS C:\Users\Admin.ollama\models>

<!-- gh-comment-id:2339667913 --> @purin-blog commented on GitHub (Sep 10, 2024): PS C:\Users\Admin\.ollama\models> ollama create -f Modelfile white_/mario transferring model data using existing layer sha256:8de95da68dc485c0889c205384c24642f83ca18d089559c977ffc6a3972a71a8 using existing layer sha256:62fbfd9ed093d6e5ac83190c86eec5369317919f4b149598d2dbb38900e9faef using existing layer sha256:c156170b718ec29139d3653d40ed1986fd92fb7e0959b5c71f3c48f62e6636f4 creating new layer sha256:b3fb3caebac98f848f5c65ff9eb77c6f3ce8cefd4fad45e94c37725ca847c562 creating new layer sha256:b1c932e03beb32c4ab61bb50b2fa06ab1f2ea4e99ee6495670bbe23834dc7d62 creating new layer sha256:ed36a163da40b1fea25ee506c2b82eb76df4878b4e2afa5db53f42f7a97639e5 writing manifest success PS C:\Users\Admin\.ollama\models> ollama push white_/mario retrieving manifest Error: file does not exist PS C:\Users\Admin\.ollama\models>
GiteaMirror commented 2026-04-12 14:58:36 -05:00
Author
Owner
Copy Link

@purin-blog commented on GitHub (Sep 10, 2024):

Always fail

<!-- gh-comment-id:2339668927 --> @purin-blog commented on GitHub (Sep 10, 2024): Always fail
GiteaMirror commented 2026-04-12 14:58:37 -05:00
Author
Owner
Copy Link

@hololeo commented on GitHub (Oct 11, 2024):

still cant do this

<!-- gh-comment-id:2407565508 --> @hololeo commented on GitHub (Oct 11, 2024): still cant do this
GiteaMirror commented 2026-04-12 14:58:37 -05:00
Author
Owner
Copy Link

@hololeo commented on GitHub (Nov 29, 2024):

still not possible

<!-- gh-comment-id:2508676370 --> @hololeo commented on GitHub (Nov 29, 2024): still not possible
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
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#4068
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?