github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 06:31:50 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13590] Internal Server Error on Model Load (EOF) #55460

New Issue
Closed
opened 2026-04-29 09:15:48 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 09:15:48 -05:00
Owner
Copy Link

Originally created by @ApprenticeofEnder on GitHub (Dec 31, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13590

What is the issue?

Attempted to run gpt-oss:20b on my local hardware, got an internal service error that said something about an EOF.

Was on 0.12.11, swapping to 0.13.5 because I'm running it via Nix and home-manager, will update if that changes anything.

Relevant log output

From systemctl --user ollama, since that's the only thing that currently gives me anything resembling logs.

ollama.service - Server for local large language models
     Loaded: loaded (/home/ender/.config/systemd/user/ollama.service; enabled; vendor preset: enabled)
     Active: active (running) since Tue 2025-12-30 22:04:39 EST; 38min ago
   Main PID: 16508 (.ollama-wrapped)
      Tasks: 22 (limit: 38009)
     Memory: 11.8G
        CPU: 1min 43.892s
     CGroup: /user.slice/user-1000.slice/user@1000.service/app.slice/ollama.service
             └─16508 /nix/store/6bxrsdj05ykag2dr9hwp8z9bhah2a0gy-ollama-0.12.11/bin/ollama serve

Dec 30 22:31:47 ender-hornet ollama[16508]: gs     0x0
Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.373-05:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB"
Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="858.0 MiB"
Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="222.8 MiB"
Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:272 msg="total memory" size="13.9 GiB"
Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=sched.go:470 msg="Load failed" model=/home/ender/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb error="do load request: Post \"http://127.0.0.1:43297/load\": EOF"
Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.418-05:00 level=ERROR source=server.go:265 msg="llama runner terminated" error="exit status 2"
Dec 30 22:31:47 ender-hornet ollama[16508]: [GIN] 2025/12/30 - 22:31:47 | 500 |  1.823233695s |       127.0.0.1 | POST     "/api/generate"

nvidia-smi:

Tue Dec 30 22:46:19 2025       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.95.05              Driver Version: 580.95.05      CUDA Version: 13.0     |
+-----------------------------------------+------------------------+----------------------+
| 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  NVIDIA GeForce GTX 980 Ti      Off |   00000000:04:00.0 Off |                  N/A |
|  0%   36C    P8             11W /  250W |       8MiB /   6144MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
|   1  NVIDIA GeForce RTX 3070 Ti     Off |   00000000:0A:00.0  On |                  N/A |
|  0%   54C    P5             41W /  290W |     857MiB /   8192MiB |     32%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A            1680      G   /usr/lib/xorg/Xorg                        3MiB |
|    1   N/A  N/A            1680      G   /usr/lib/xorg/Xorg                      434MiB |
|    1   N/A  N/A            2686      G   cinnamon                                 16MiB |
|    1   N/A  N/A            2994      G   /opt/1Password/1password                 23MiB |
|    1   N/A  N/A            3150      G   .../ender/.nix-profile/bin/kitty         13MiB |
|    1   N/A  N/A           18347      G   /usr/lib/firefox/firefox                236MiB |
+-----------------------------------------------------------------------------------------+

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.12.11

Originally created by @ApprenticeofEnder on GitHub (Dec 31, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13590 ### What is the issue? Attempted to run `gpt-oss:20b` on my local hardware, got an internal service error that said something about an EOF. Was on 0.12.11, swapping to 0.13.5 because I'm running it via Nix and home-manager, will update if that changes anything. ### Relevant log output From `systemctl --user ollama`, since that's the only thing that currently gives me anything resembling logs. ``` ollama.service - Server for local large language models Loaded: loaded (/home/ender/.config/systemd/user/ollama.service; enabled; vendor preset: enabled) Active: active (running) since Tue 2025-12-30 22:04:39 EST; 38min ago Main PID: 16508 (.ollama-wrapped) Tasks: 22 (limit: 38009) Memory: 11.8G CPU: 1min 43.892s CGroup: /user.slice/user-1000.slice/user@1000.service/app.slice/ollama.service └─16508 /nix/store/6bxrsdj05ykag2dr9hwp8z9bhah2a0gy-ollama-0.12.11/bin/ollama serve Dec 30 22:31:47 ender-hornet ollama[16508]: gs 0x0 Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.373-05:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB" Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="858.0 MiB" Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="222.8 MiB" Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=device.go:272 msg="total memory" size="13.9 GiB" Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.374-05:00 level=INFO source=sched.go:470 msg="Load failed" model=/home/ender/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb error="do load request: Post \"http://127.0.0.1:43297/load\": EOF" Dec 30 22:31:47 ender-hornet ollama[16508]: time=2025-12-30T22:31:47.418-05:00 level=ERROR source=server.go:265 msg="llama runner terminated" error="exit status 2" Dec 30 22:31:47 ender-hornet ollama[16508]: [GIN] 2025/12/30 - 22:31:47 | 500 | 1.823233695s | 127.0.0.1 | POST "/api/generate" ``` `nvidia-smi`: ``` Tue Dec 30 22:46:19 2025 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 | +-----------------------------------------+------------------------+----------------------+ | 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 NVIDIA GeForce GTX 980 Ti Off | 00000000:04:00.0 Off | N/A | | 0% 36C P8 11W / 250W | 8MiB / 6144MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ | 1 NVIDIA GeForce RTX 3070 Ti Off | 00000000:0A:00.0 On | N/A | | 0% 54C P5 41W / 290W | 857MiB / 8192MiB | 32% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1680 G /usr/lib/xorg/Xorg 3MiB | | 1 N/A N/A 1680 G /usr/lib/xorg/Xorg 434MiB | | 1 N/A N/A 2686 G cinnamon 16MiB | | 1 N/A N/A 2994 G /opt/1Password/1password 23MiB | | 1 N/A N/A 3150 G .../ender/.nix-profile/bin/kitty 13MiB | | 1 N/A N/A 18347 G /usr/lib/firefox/firefox 236MiB | +-----------------------------------------------------------------------------------------+ ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.12.11
GiteaMirror added the bug label 2026-04-29 09:15:48 -05:00
GiteaMirror commented 2026-04-29 09:15:52 -05:00
Author
Owner
Copy Link

@ApprenticeofEnder commented on GitHub (Dec 31, 2025):

Updating to 0.13.5 seems to have resolved it. Strange.

<!-- gh-comment-id:3701410130 --> @ApprenticeofEnder commented on GitHub (Dec 31, 2025): Updating to 0.13.5 seems to have resolved it. Strange.
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#55460
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?