github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6516] OLLAMA_NUM_PARALLEL with Gemma-2-9B model #50614

New Issue
Closed
opened 2026-04-28 16:32:46 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 16:32:46 -05:00
Owner
Copy Link

Originally created by @lihkinVerma on GitHub (Aug 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6516

What is the issue?

When either steting the OLLAMA_NUM_PARALLEL varaible to value greater than 1 in ollama.service or in docker run command (sudo docker run -d --gpus=all -v ollama:/root/.ollama -p 9000:11434 -e OLLAMA_NUM_PARALLEL=10 -e OLLAMA_MAX_LOADED_MODELS=4 --name ollama ollama/ollama) it do not works properly, if running model gemma2:9b-instruct-fp16

Either the docker container do not starts or if running with ollama.service then the command starts with variable --parallel 1

This is not the case with other models like phi-3.5, llama-3.1 or even gemma2:2b-instruct-fp16

Can you please check the issue?

I am using RTX4090, with single node having 4 GPUs each of VRAM 8GB in size

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.5

Originally created by @lihkinVerma on GitHub (Aug 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6516 ### What is the issue? When either steting the OLLAMA_NUM_PARALLEL varaible to value greater than 1 in ollama.service or in docker run command (`sudo docker run -d --gpus=all -v ollama:/root/.ollama -p 9000:11434 -e OLLAMA_NUM_PARALLEL=10 -e OLLAMA_MAX_LOADED_MODELS=4 --name ollama ollama/ollama`) it do not works properly, if running model gemma2:9b-instruct-fp16 Either the docker container do not starts or if running with ollama.service then the command starts with variable --parallel 1 This is not the case with other models like phi-3.5, llama-3.1 or even gemma2:2b-instruct-fp16 Can you please check the issue? I am using RTX4090, with single node having 4 GPUs each of VRAM 8GB in size ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.5
GiteaMirror added the bug label 2026-04-28 16:32:46 -05:00
GiteaMirror commented 2026-04-28 16:32:49 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 26, 2024):

Hi @lihkinVerma can you try with version 0.3.7-rc6 ?

https://github.com/ollama/ollama/releases/tag/v0.3.7-rc6

<!-- gh-comment-id:2310204931 --> @igorschlum commented on GitHub (Aug 26, 2024): Hi @lihkinVerma can you try with version 0.3.7-rc6 ? https://github.com/ollama/ollama/releases/tag/v0.3.7-rc6
GiteaMirror commented 2026-04-28 16:32:50 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 26, 2024):

Fixed with https://github.com/ollama/ollama/pull/6402, as per igorschlum 0.3.7-rc6 should work.

<!-- gh-comment-id:2310689845 --> @rick-github commented on GitHub (Aug 26, 2024): Fixed with https://github.com/ollama/ollama/pull/6402, as per igorschlum 0.3.7-rc6 should work.
GiteaMirror commented 2026-04-28 16:32:51 -05:00
Author
Owner
Copy Link

@lihkinVerma commented on GitHub (Aug 26, 2024):

Thankyou using the latest version, fixed the issue (0.3.7-rc6)

<!-- gh-comment-id:2310956144 --> @lihkinVerma commented on GitHub (Aug 26, 2024): Thankyou using the latest version, fixed the issue (0.3.7-rc6)
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#50614
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?