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 #6903] nexusraven:13b-v2-q2_K EOF #50878

New Issue
Closed
opened 2026-04-28 17:19:28 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 17:19:28 -05:00
Owner
Copy Link

Originally created by @shuther on GitHub (Sep 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6903

What is the issue?

either using the API or the CLI, I can't get nexusraven:13b-v2-q2_K to work (other models work fine)

ollama pull nexusraven:13b-v2-q2_K
OLLAMA_DEBUG="1" ollama run nexusraven:13b-v2-q2_K
Error: Post "http://127.0.0.1:11434/api/generate": EOF

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.3.11

Originally created by @shuther on GitHub (Sep 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6903 ### What is the issue? either using the API or the CLI, I can't get nexusraven:13b-v2-q2_K to work (other models work fine) ``` ollama pull nexusraven:13b-v2-q2_K OLLAMA_DEBUG="1" ollama run nexusraven:13b-v2-q2_K Error: Post "http://127.0.0.1:11434/api/generate": EOF ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.3.11
GiteaMirror added the needs more infobug labels 2026-04-28 17:19:28 -05:00
GiteaMirror commented 2026-04-28 17:19:32 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 22, 2024):

Server logs will aid in debugging. Also, for OLLAMA_DEBUG="1" to have an effect, it needs to be set in the environment of the server.

<!-- gh-comment-id:2365367556 --> @rick-github commented on GitHub (Sep 22, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in debugging. Also, for `OLLAMA_DEBUG="1" ` to have an effect, it needs to be [set in the environment of the server](https://github.com/ollama/ollama/blob/main/docs/faq.md#setting-environment-variables-on-linux).
GiteaMirror commented 2026-04-28 17:19:32 -05:00
Author
Owner
Copy Link

@shuther commented on GitHub (Sep 22, 2024):

ollama is killed by the oom-killer.
My expectation was than I would need less than 6GB to run it, as per: https://ollama.com/library/nexusraven:13b-v2-q2_K? I would love if somebody could tell me why I was wrong, or ollama requires more during the loading phase of the model?

Even with 6GB it failed with: echo 6G > /sys/fs/cgroup/system.slice/ollama.service/memory.max
I was able to make it work with 8G. At the end ollama was using about 5.5G of RAM and 4.2G on the nvidia card.
Hope it helps others

sudo systemctl set-property ollama.service MemoryMax=8G

# Edit the unit file
sudo systemctl edit ollama.service

# Add the MemoryMax setting
# In the editor, add:
# [Service]
# MemoryMax=4G
<!-- gh-comment-id:2366748620 --> @shuther commented on GitHub (Sep 22, 2024): ollama is killed by the oom-killer. My expectation was than I would need less than 6GB to run it, as per: https://ollama.com/library/nexusraven:13b-v2-q2_K? I **would love if somebody could tell me why I was wrong, or ollama requires more during the loading phase of the model?** Even with 6GB it failed with: `echo 6G > /sys/fs/cgroup/system.slice/ollama.service/memory.max` I was able to make it work with 8G. At the end ollama was using about 5.5G of RAM and 4.2G on the nvidia card. Hope it helps others `sudo systemctl set-property ollama.service MemoryMax=8G` ``` # Edit the unit file sudo systemctl edit ollama.service # Add the MemoryMax setting # In the editor, add: # [Service] # MemoryMax=4G ```
GiteaMirror commented 2026-04-28 17:19:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 22, 2024):

7.4G VRAM in total, search for layers.offload in the server logs.

<!-- gh-comment-id:2366755463 --> @rick-github commented on GitHub (Sep 22, 2024): 7.4G VRAM in total, search for `layers.offload` in the [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-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 needs more info
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#50878
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?