github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9817] update to 0.6.1, the model seems don't be loaded to th vram #32186

New Issue
Closed
opened 2026-04-22 13:13:40 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 13:13:40 -05:00
Owner
Copy Link

Originally created by @itsmeaningless on GitHub (Mar 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9817

What is the issue?

output of command(ollama ps):
NAME ID SIZE PROCESSOR UNTIL
google_gemma-3-27b-it-IQ4_XS.gguf:latest b7aea856d9f1 18 GB 10%/90% CPU/GPU 4 minutes from now

output of nvidia-smi
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 570.124.04 Driver Version: 570.124.04 CUDA Version: 12.8 |
|-----------------------------------------+------------------------+----------------------+
| 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 RTX 4080 ... Off | 00000000:01:00.0 Off | N/A |
| 0% 37C P8 4W / 320W | 39MiB / 16376MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 1805 G /usr/lib/xorg/Xorg 9MiB |
| 0 N/A N/A 1937 G /usr/bin/gnome-shell 6MiB |
+-----------------------------------------------------------------------------------------+

output of log:
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: loading model tensors, this can take a while... (mmap = true)
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 0 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 1 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 2 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 3 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 4 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 5 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 6 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 7 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 8 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 9 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 10 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 11 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 12 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 13 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 14 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 15 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 16 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 17 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 18 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 19 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 20 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 21 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 22 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 23 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 24 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 25 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 26 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 27 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 28 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 29 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 30 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 31 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 32 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 33 assigned to device CPU
3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 34 assigned to device CPU

Relevant log output

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.6.1

Originally created by @itsmeaningless on GitHub (Mar 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9817 ### What is the issue? **output of command(ollama ps):** NAME ID SIZE PROCESSOR UNTIL google_gemma-3-27b-it-IQ4_XS.gguf:latest b7aea856d9f1 18 GB 10%/90% CPU/GPU 4 minutes from now **output of nvidia-smi** +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 570.124.04 Driver Version: 570.124.04 CUDA Version: 12.8 | |-----------------------------------------+------------------------+----------------------+ | 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 RTX 4080 ... Off | 00000000:01:00.0 Off | N/A | | 0% 37C P8 4W / 320W | 39MiB / 16376MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1805 G /usr/lib/xorg/Xorg 9MiB | | 0 N/A N/A 1937 G /usr/bin/gnome-shell 6MiB | +-----------------------------------------------------------------------------------------+ **output of log:** 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: loading model tensors, this can take a while... (mmap = true) 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 0 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 1 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 2 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 3 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 4 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 5 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 6 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 7 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 8 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 9 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 10 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 11 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 12 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 13 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 14 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 15 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 16 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 17 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 18 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 19 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 20 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 21 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 22 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 23 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 24 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 25 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 26 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 27 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 28 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 29 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 30 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 31 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 32 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 33 assigned to device CPU 3月 17 17:28:06 dy-canvas ollama[73083]: load_tensors: layer 34 assigned to device CPU ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.6.1
GiteaMirror added the bug label 2026-04-22 13:13:40 -05:00
GiteaMirror commented 2026-04-22 13:13:42 -05:00
Author
Owner
Copy Link

@itsmeaningless commented on GitHub (Mar 17, 2025):

reboot the machaine, work well

<!-- gh-comment-id:2728941533 --> @itsmeaningless commented on GitHub (Mar 17, 2025): reboot the machaine, work well
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#32186
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?