github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3667] exception create_tensor: tensor 'blk.0.ffn_gate.0.weight' not found #2258

New Issue
Closed
opened 2026-04-12 12:31:55 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 12:31:55 -05:00
Owner
Copy Link

Originally created by @nkeilar on GitHub (Apr 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3667

What is the issue?

Getting this error when trying to use wizardlm2:8x22b-q2_K on a dual 3090 system.

image

ollama version is 0.1.31

Someone else is having same issue in this thread, but I think its a new issue:

https://github.com/ollama/ollama/issues/3032#issuecomment-2058129280

What did you expect to see?

Model loads into memory

Steps to reproduce

Install latest Ollama, try load the wizardlm2:8x22b-q2_K model

Are there any recent changes that introduced the issue?

No response

OS

Linux

Architecture

amd64

Platform

No response

Ollama version

0.1.31

GPU

Nvidia

GPU info

ue Apr 16 14:09:48 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.54.15 Driver Version: 550.54.15 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| 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 3090 Off | 00000000:01:00.0 On | N/A |
| 33% 43C P5 48W / 350W | 1429MiB / 24576MiB | 23% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 1 NVIDIA GeForce RTX 3090 Off | 00000000:08:00.0 Off | N/A |
| 30% 35C P8 25W / 200W | 276MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 3657 G /usr/lib/xorg/Xorg 654MiB |
| 0 N/A N/A 4314 G /usr/bin/gnome-shell 82MiB |
| 0 N/A N/A 10313 G /usr/bin/nextcloud 82MiB |
| 0 N/A N/A 911826 C /usr/local/bin/ollama 260MiB |
| 0 N/A N/A 1525117 G ...onEnabled --variations-seed-version 36MiB |
| 0 N/A N/A 3518670 G /usr/lib/firefox/firefox 198MiB |
| 1 N/A N/A 3657 G /usr/lib/xorg/Xorg 4MiB |
| 1 N/A N/A 911826 C /usr/local/bin/ollama 260MiB |
+-----------------------------------------------------------------------------------------+

CPU

Intel

Other software

No response

Originally created by @nkeilar on GitHub (Apr 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3667 ### What is the issue? Getting this error when trying to use wizardlm2:8x22b-q2_K on a dual 3090 system. ![image](https://github.com/ollama/ollama/assets/325430/e80c8180-0b82-43d9-8625-ffa795045bfc) ollama version is 0.1.31 Someone else is having same issue in this thread, but I think its a new issue: https://github.com/ollama/ollama/issues/3032#issuecomment-2058129280 ### What did you expect to see? Model loads into memory ### Steps to reproduce Install latest Ollama, try load the wizardlm2:8x22b-q2_K model ### Are there any recent changes that introduced the issue? _No response_ ### OS Linux ### Architecture amd64 ### Platform _No response_ ### Ollama version 0.1.31 ### GPU Nvidia ### GPU info ue Apr 16 14:09:48 2024 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 550.54.15 Driver Version: 550.54.15 CUDA Version: 12.4 | |-----------------------------------------+------------------------+----------------------+ | 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 3090 Off | 00000000:01:00.0 On | N/A | | 33% 43C P5 48W / 350W | 1429MiB / 24576MiB | 23% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ | 1 NVIDIA GeForce RTX 3090 Off | 00000000:08:00.0 Off | N/A | | 30% 35C P8 25W / 200W | 276MiB / 24576MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 3657 G /usr/lib/xorg/Xorg 654MiB | | 0 N/A N/A 4314 G /usr/bin/gnome-shell 82MiB | | 0 N/A N/A 10313 G /usr/bin/nextcloud 82MiB | | 0 N/A N/A 911826 C /usr/local/bin/ollama 260MiB | | 0 N/A N/A 1525117 G ...onEnabled --variations-seed-version 36MiB | | 0 N/A N/A 3518670 G /usr/lib/firefox/firefox 198MiB | | 1 N/A N/A 3657 G /usr/lib/xorg/Xorg 4MiB | | 1 N/A N/A 911826 C /usr/local/bin/ollama 260MiB | +-----------------------------------------------------------------------------------------+ ### CPU Intel ### Other software _No response_
GiteaMirror added the bug label 2026-04-12 12:31:55 -05:00
GiteaMirror commented 2026-04-12 12:31:56 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Apr 16, 2024):

Hi there, sorry this isn't more apparent in the error, but the new 8x22b models require Ollama 0.1.32 which will be released soon – in the meantime you can install the prerelease from https://github.com/ollama/ollama/releases/tag/v0.1.32

Hope this helps!

<!-- gh-comment-id:2058196510 --> @jmorganca commented on GitHub (Apr 16, 2024): Hi there, sorry this isn't more apparent in the error, but the new 8x22b models require Ollama 0.1.32 which will be released soon – in the meantime you can install the prerelease from https://github.com/ollama/ollama/releases/tag/v0.1.32 Hope this helps!
GiteaMirror commented 2026-04-12 12:31:56 -05:00
Author
Owner
Copy Link

@nkeilar commented on GitHub (Apr 16, 2024):

Okay, sorry - just found this - https://github.com/ggerganov/llama.cpp/issues/6665 which seems related. Sounds like it will be out soon.

<!-- gh-comment-id:2058197958 --> @nkeilar commented on GitHub (Apr 16, 2024): Okay, sorry - just found this - https://github.com/ggerganov/llama.cpp/issues/6665 which seems related. Sounds like it will be out soon.
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#2258
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?