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 #10588] Ollama doesn't use GPU anymore #69026

New Issue
Closed
opened 2026-05-04 16:54:07 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 16:54:07 -05:00
Owner
Copy Link

Originally created by @TheEisbaer on GitHub (May 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10588

What is the issue?

I am trying to use qwen3, after updating to 0.6.8 stopped using GPU

Relevant log output

source=memory.go:194 msg="gpu has too little memory to allocate any layers" id=GPU-152ad784-f966-afea-c7eb-3ef56b5c7522 library=cuda variant=v12 compute=8.9 driver=12.8 name="NVIDIA RTX 2000 Ada Generation Laptop GPU" total="8.0 GiB" available="6.9 GiB" minimum_memory=479199232 layer_size="375.6 MiB" gpu_zer_overhead="0 B" partial_offload="6.0 GiB" full_offload="6.0 GiB"

OS

WSL2

GPU

AMD, Nvidia

CPU

Intel

Ollama version

0.6.8

Originally created by @TheEisbaer on GitHub (May 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10588 ### What is the issue? I am trying to use qwen3, after updating to 0.6.8 stopped using GPU ### Relevant log output ```shell source=memory.go:194 msg="gpu has too little memory to allocate any layers" id=GPU-152ad784-f966-afea-c7eb-3ef56b5c7522 library=cuda variant=v12 compute=8.9 driver=12.8 name="NVIDIA RTX 2000 Ada Generation Laptop GPU" total="8.0 GiB" available="6.9 GiB" minimum_memory=479199232 layer_size="375.6 MiB" gpu_zer_overhead="0 B" partial_offload="6.0 GiB" full_offload="6.0 GiB" ``` ### OS WSL2 ### GPU AMD, Nvidia ### CPU Intel ### Ollama version 0.6.8
GiteaMirror added the bug label 2026-05-04 16:54:07 -05:00
GiteaMirror commented 2026-05-04 16:54:17 -05:00
Author
Owner
Copy Link

@TheEisbaer commented on GitHub (May 6, 2025):

My mistake, set 65k context size but default qwen3 only supports 32k

<!-- gh-comment-id:2853967940 --> @TheEisbaer commented on GitHub (May 6, 2025): My mistake, set 65k context size but default qwen3 only supports 32k
GiteaMirror commented 2026-05-04 16:54:19 -05:00
Author
Owner
Copy Link

@AlessandroSpallina commented on GitHub (May 9, 2025):

Context size of qwen3 in Ollama isn’t clear to me. My understanding is that qwen3 support 32K context but that can be increased up to 120K with YaRN; is this the case in Ollama?

Moreover, anyone have tried the qwen3 suggested parameters with RAG use cases? Alibaba suggests temperature around 0.7..

<!-- gh-comment-id:2867580120 --> @AlessandroSpallina commented on GitHub (May 9, 2025): Context size of qwen3 in Ollama isn’t clear to me. My understanding is that qwen3 support 32K context but that can be increased up to 120K with YaRN; is this the case in Ollama? Moreover, anyone have tried the qwen3 suggested parameters with RAG use cases? Alibaba suggests temperature around 0.7..
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#69026
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?