github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9846] Error: digest mismatch, file must be downloaded again: want sha256:8de95da68dc485c0889c205384c24642f83ca18d089559c977ffc6a3972a71a8, got sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855 #52959

New Issue
Open
opened 2026-04-29 01:28:23 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-29 01:28:23 -05:00
Owner
Copy Link

Originally created by @yisheng926 on GitHub (Mar 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9846

What is the issue?

Image

Relevant log output

time=2025-03-18T09:46:40.265+08:00 level=INFO source=images.go:432 msg="total blobs: 0"
time=2025-03-18T09:46:40.265+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-03-18T09:46:40.265+08:00 level=INFO source=routes.go:1297 msg="Listening on 127.0.0.1:11434 (version 0.6.1)"
time=2025-03-18T09:46:40.265+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-03-18T09:46:40.265+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-03-18T09:46:40.265+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-03-18T09:46:40.265+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=14 efficiency=8 threads=20
time=2025-03-18T09:46:40.299+08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-03-18T09:46:40.299+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="15.6 GiB" available="8.1 GiB"
[GIN] 2025/03/18 - 09:47:08 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/03/18 - 09:47:17 | 200 |       509.9µs |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/03/18 - 09:47:27 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/03/18 - 09:47:27 | 404 |       515.8µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/03/18 - 09:47:32 | 200 |    5.7646472s |       127.0.0.1 | POST     "/api/pull"

OS

Windows

GPU

No response

CPU

Intel

Ollama version

0.6.1

Originally created by @yisheng926 on GitHub (Mar 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9846 ### What is the issue? ![Image](https://github.com/user-attachments/assets/3f37746a-c5fe-4819-950b-fea8ed415890) ### Relevant log output ```shell time=2025-03-18T09:46:40.265+08:00 level=INFO source=images.go:432 msg="total blobs: 0" time=2025-03-18T09:46:40.265+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-03-18T09:46:40.265+08:00 level=INFO source=routes.go:1297 msg="Listening on 127.0.0.1:11434 (version 0.6.1)" time=2025-03-18T09:46:40.265+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-03-18T09:46:40.265+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-03-18T09:46:40.265+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-03-18T09:46:40.265+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=14 efficiency=8 threads=20 time=2025-03-18T09:46:40.299+08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-03-18T09:46:40.299+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="15.6 GiB" available="8.1 GiB" [GIN] 2025/03/18 - 09:47:08 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/03/18 - 09:47:17 | 200 | 509.9µs | 127.0.0.1 | GET "/api/version" [GIN] 2025/03/18 - 09:47:27 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/03/18 - 09:47:27 | 404 | 515.8µs | 127.0.0.1 | POST "/api/show" [GIN] 2025/03/18 - 09:47:32 | 200 | 5.7646472s | 127.0.0.1 | POST "/api/pull" ``` ### OS Windows ### GPU _No response_ ### CPU Intel ### Ollama version 0.6.1
GiteaMirror added the networkingbug labels 2026-04-29 01:28:23 -05:00
GiteaMirror commented 2026-04-29 01:28:25 -05:00
Author
Owner
Copy Link

@alterfo commented on GitHub (Mar 19, 2025):

The same for command-a. Ollama 0.6.2

Image
<!-- gh-comment-id:2738237365 --> @alterfo commented on GitHub (Mar 19, 2025): The same for command-a. Ollama 0.6.2 <img width="1346" alt="Image" src="https://github.com/user-attachments/assets/a2857ad8-f9b5-41c6-b307-d5d1b1552f94" />
GiteaMirror commented 2026-04-29 01:28:28 -05:00
Author
Owner
Copy Link

@croqaz commented on GitHub (Mar 25, 2025):

The same error:

ollama pull gemma3:12b
pulling manifest
pulling e8ad13eff07a... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏ 8.1 GB
pulling e0a42594d802... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏  358 B
pulling dd084c7d92a3... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏ 8.4 KB
pulling 3116c5225075... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏   77 B
pulling 6819964c2bcf... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏  490 B
verifying sha256 digest
Error: digest mismatch, file must be downloaded again: want sha256:e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de, got sha256:9f2c6af225bcd3a39b783b5f2063eb0d95ddd2d845799a9aa529c438299d3eec

[GIN] 2025/03/25 - 11:39:27 | 200 |     869.292µs |       127.0.0.1 | HEAD     "/"
time=2025-03-25T11:39:29.130Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)"
[GIN] 2025/03/25 - 12:12:37 | 200 |         33m9s |       127.0.0.1 | POST     "/api/pull"
[GIN] 2025/03/25 - 12:12:38 | 200 |      15.666µs |       127.0.0.1 | HEAD     "/"
time=2025-03-25T12:12:39.313Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)"
time=2025-03-25T12:12:51.477Z level=INFO source=download.go:294 msg="e8ad13eff07a part 4 attempt 0 failed: Get \"https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/e8/e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20250325%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250325T121239Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=ecdb5354c49bd076b6318b3177ad5d73e99d75b4a0fef77e8c68e062cd59a534\": net/http: TLS handshake timeout, retrying in 1s"
[GIN] 2025/03/25 - 12:35:14 | 200 |      16.916µs |       127.0.0.1 | HEAD     "/"
time=2025-03-25T12:35:14.915Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)"
[GIN] 2025/03/25 - 13:30:53 | 200 |     748.084µs |       127.0.0.1 | HEAD     "/"
time=2025-03-25T13:30:54.365Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)"
[GIN] 2025/03/25 - 13:41:54 | 200 |      15.583µs |       127.0.0.1 | HEAD     "/"
time=2025-03-25T13:43:21.009Z level=INFO source=download.go:176 msg="downloading 3116c5225075 in 1 77 B part(s)"
time=2025-03-25T13:43:22.708Z level=INFO source=download.go:176 msg="downloading 6819964c2bcf in 1 490 B part(s)"
[GIN] 2025/03/25 - 13:47:07 | 200 |      16.583µs |       127.0.0.1 | HEAD     "/"
time=2025-03-25T13:47:09.220Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)"
[GIN] 2025/03/25 - 13:47:13 | 200 |  5.677087708s |       127.0.0.1 | POST     "/api/pull"

This is a big problem for me... I don't have land internet, I'm tethering from my phone and after 2 hours of waiting for the model to download, I get his error, every single time...
This is the 3rd day I'm trying, with a very similar error.

Not sure how to get any model which is larger than 4GB, I suppose my only hope is to try to download the models directly from Huggingface with a stable app, maybe huggingface_hub ?

<!-- gh-comment-id:2751358928 --> @croqaz commented on GitHub (Mar 25, 2025): The same error: ``` ollama pull gemma3:12b pulling manifest pulling e8ad13eff07a... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏ 8.1 GB pulling e0a42594d802... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏ 358 B pulling dd084c7d92a3... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏ 8.4 KB pulling 3116c5225075... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏ 77 B pulling 6819964c2bcf... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████▏ 490 B verifying sha256 digest Error: digest mismatch, file must be downloaded again: want sha256:e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de, got sha256:9f2c6af225bcd3a39b783b5f2063eb0d95ddd2d845799a9aa529c438299d3eec ``` ``` [GIN] 2025/03/25 - 11:39:27 | 200 | 869.292µs | 127.0.0.1 | HEAD "/" time=2025-03-25T11:39:29.130Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)" [GIN] 2025/03/25 - 12:12:37 | 200 | 33m9s | 127.0.0.1 | POST "/api/pull" [GIN] 2025/03/25 - 12:12:38 | 200 | 15.666µs | 127.0.0.1 | HEAD "/" time=2025-03-25T12:12:39.313Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)" time=2025-03-25T12:12:51.477Z level=INFO source=download.go:294 msg="e8ad13eff07a part 4 attempt 0 failed: Get \"https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/e8/e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de/data?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=66040c77ac1b787c3af820529859349a%2F20250325%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250325T121239Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=ecdb5354c49bd076b6318b3177ad5d73e99d75b4a0fef77e8c68e062cd59a534\": net/http: TLS handshake timeout, retrying in 1s" [GIN] 2025/03/25 - 12:35:14 | 200 | 16.916µs | 127.0.0.1 | HEAD "/" time=2025-03-25T12:35:14.915Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)" [GIN] 2025/03/25 - 13:30:53 | 200 | 748.084µs | 127.0.0.1 | HEAD "/" time=2025-03-25T13:30:54.365Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)" [GIN] 2025/03/25 - 13:41:54 | 200 | 15.583µs | 127.0.0.1 | HEAD "/" time=2025-03-25T13:43:21.009Z level=INFO source=download.go:176 msg="downloading 3116c5225075 in 1 77 B part(s)" time=2025-03-25T13:43:22.708Z level=INFO source=download.go:176 msg="downloading 6819964c2bcf in 1 490 B part(s)" [GIN] 2025/03/25 - 13:47:07 | 200 | 16.583µs | 127.0.0.1 | HEAD "/" time=2025-03-25T13:47:09.220Z level=INFO source=download.go:176 msg="downloading e8ad13eff07a in 16 509 MB part(s)" [GIN] 2025/03/25 - 13:47:13 | 200 | 5.677087708s | 127.0.0.1 | POST "/api/pull" ``` This is a big problem for me... I don't have land internet, I'm tethering from my phone and after 2 hours of waiting for the model to download, I get his error, every single time... This is the 3rd day I'm trying, with a very similar error. Not sure how to get any model which is larger than 4GB, I suppose my only hope is to try to download the models directly from Huggingface with a stable app, maybe huggingface_hub ?
GiteaMirror commented 2026-04-29 01:28:28 -05:00
Author
Owner
Copy Link

@ericzon commented on GitHub (Apr 15, 2025):

I have the same error using latest version 0.6.5

<!-- gh-comment-id:2805153928 --> @ericzon commented on GitHub (Apr 15, 2025): I have the same error using latest version 0.6.5
GiteaMirror commented 2026-04-29 01:28:30 -05:00
Author
Owner
Copy Link

@croqaz commented on GitHub (Apr 16, 2025):

I stopped using Ollama because of this error, I'm now downloading the models with wget --continue ...(HuggingFace GGUF file).
I'm serving them with either Llama.cpp, or Kobold.cpp, or Llamafile. For interface, there are lots of options, my fav is LM-Studio, and I'm doing my own text-based chat system that works with OpenAI-compatible APIs.

<!-- gh-comment-id:2809428357 --> @croqaz commented on GitHub (Apr 16, 2025): I stopped using Ollama because of this error, I'm now downloading the models with `wget --continue ...(HuggingFace GGUF file)`. I'm serving them with either Llama.cpp, or Kobold.cpp, or Llamafile. For interface, there are lots of options, my fav is LM-Studio, and I'm doing my own text-based chat system that works with OpenAI-compatible APIs.
GiteaMirror commented 2026-04-29 01:28:30 -05:00
Author
Owner
Copy Link

@anirbanbasu commented on GitHub (Aug 23, 2025):

Try https://github.com/anirbanbasu/ollama-downloader -- it has worked for me even behind a HTTPS proxy with a self-signed certificate. (Disclaimer: I am the maintainer of the project.)

<!-- gh-comment-id:3216790360 --> @anirbanbasu commented on GitHub (Aug 23, 2025): Try https://github.com/anirbanbasu/ollama-downloader -- it has worked for me even behind a HTTPS proxy with a self-signed certificate. (Disclaimer: I am the maintainer of the project.)
GiteaMirror commented 2026-04-29 01:28:31 -05:00
Author
Owner
Copy Link

@jeiber commented on GitHub (Nov 7, 2025):

Troubleshooting with Claude for about an hour:

"✅ Mistral 4.4 GB — success
✅ Llama2 3.8 GB — success
❌ Gemma3 17 GB — digest mismatch

This is almost certainly a gemma3-specific issue on the Ollama registry. The model blob itself may be corrupted or the manifest hash is wrong."

ollama pull gemma3:27b
pulling manifest
pulling e796792eba26: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 17 GB
pulling e0a42594d802: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 358 B
pulling dd084c7d92a3: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 8.4 KB
pulling 3116c5225075: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 77 B
pulling f838f048d368: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 490 B
verifying sha256 digest
Error: digest mismatch, file must be downloaded again: want sha256:e796792eba26c4d3b04b0ac5adb01a453dd9ec2dfd83b6c59cbf6fe5f30b0f68, got sha256:1d6b7b8c11aca963a282696694e22630f1fc10ef8408baa3e2d9c1f8040b408b

<!-- gh-comment-id:3500125929 --> @jeiber commented on GitHub (Nov 7, 2025): Troubleshooting with Claude for about an hour: "✅ Mistral 4.4 GB — success ✅ Llama2 3.8 GB — success ❌ Gemma3 17 GB — digest mismatch This is almost certainly a gemma3-specific issue on the Ollama registry. The model blob itself may be corrupted or the manifest hash is wrong." ollama pull gemma3:27b pulling manifest pulling e796792eba26: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 17 GB pulling e0a42594d802: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 358 B pulling dd084c7d92a3: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 8.4 KB pulling 3116c5225075: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 77 B pulling f838f048d368: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 490 B verifying sha256 digest Error: digest mismatch, file must be downloaded again: want sha256:e796792eba26c4d3b04b0ac5adb01a453dd9ec2dfd83b6c59cbf6fe5f30b0f68, got sha256:1d6b7b8c11aca963a282696694e22630f1fc10ef8408baa3e2d9c1f8040b408b
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#52959
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?