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 #15063] Running DeepSeek R1 model become slow #35427

New Issue
Closed
opened 2026-04-22 19:55:46 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 19:55:46 -05:00
Owner
Copy Link

Originally created by @constantin-ungureanu-github on GitHub (Mar 25, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15063

What is the issue?

With some previous ollama releases I could run deepseek-r1:70b (42GB) fast with GPU support.
However, with newer versions of ollama (noticed starting 0.18.0), the same model and same hardware now is very slow.
I see that DRAM is heavily used, same processor. But also VRAM is loaded.
Combined VRAM of 2 5090 is 64 GB, it should fit into VRAM, no? At least previously it did (I recall version 0.16.x was running in GPU/VRAM, can't recall about 0.17.x) and it was fast with DeepSeek R1.

Other models I see that are run in GPU/VRAM ex. qwen3-coder-next/51 GB. This seems a regression.

Relevant log output

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.18.x

Originally created by @constantin-ungureanu-github on GitHub (Mar 25, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15063 ### What is the issue? With some previous ollama releases I could run deepseek-r1:70b (42GB) fast with GPU support. However, with newer versions of ollama (noticed starting 0.18.0), the same model and same hardware now is very slow. I see that DRAM is heavily used, same processor. But also VRAM is loaded. Combined VRAM of 2 5090 is 64 GB, it should fit into VRAM, no? At least previously it did (I recall version 0.16.x was running in GPU/VRAM, can't recall about 0.17.x) and it was fast with DeepSeek R1. Other models I see that are run in GPU/VRAM ex. qwen3-coder-next/51 GB. This seems a regression. ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.18.x
GiteaMirror added the bug label 2026-04-22 19:55:46 -05:00
GiteaMirror commented 2026-04-22 19:55:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 25, 2026):

Server logs will aid in debugging.

<!-- gh-comment-id:4129803717 --> @rick-github commented on GitHub (Mar 25, 2026): [Server logs](https://docs.ollama.com/troubleshooting) will aid in debugging.
GiteaMirror commented 2026-04-22 19:55:48 -05:00
Author
Owner
Copy Link

@constantin-ungureanu-github commented on GitHub (Apr 13, 2026):

I solved this issue by using vllm.

<!-- gh-comment-id:4239756640 --> @constantin-ungureanu-github commented on GitHub (Apr 13, 2026): I solved this issue by using vllm.
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#35427
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?