github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11640] gemma3n:e2b no offload on NVIDIA GeForce RTX 3050 Laptop GPU #69752

New Issue
Closed
opened 2026-05-04 19:06:35 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 19:06:35 -05:00
Owner
Copy Link

Originally created by @gianlen on GitHub (Aug 2, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11640

What is the issue?

server.log
Using gemma3n, it seems that there is no offloading on gpu, while gemma3 seems fine.

Relevant log output

Device 0: NVIDIA GeForce RTX 3050 Laptop GPU, compute capability 8.6, VMM: yes
load_backend: loaded CUDA backend from C:\Users\gianl\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll
load_backend: loaded CPU backend from C:\Users\gianl\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2025-08-02T12:32:35.697+02:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-08-02T12:32:35.763+02:00 level=INFO source=ggml.go:365 msg="offloading 0 repeating layers to GPU"
time=2025-08-02T12:32:35.763+02:00 level=INFO source=ggml.go:369 msg="offloading output layer to CPU"
time=2025-08-02T12:32:35.763+02:00 level=INFO source=ggml.go:376 msg="offloaded 0/31 layers to GPU"
time=2025-08-02T12:32:35.763+02:00 level=INFO source=ggml.go:379 msg="model weights" buffer=CPU size="5.6 GiB"
time=2025-08-02T12:32:35.782+02:00 level=INFO source=ggml.go:668 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="0 B"
time=2025-08-02T12:32:35.782+02:00 level=INFO source=ggml.go:668 msg="compute graph" backend=CPU buffer_type=CPU size="123.0 MiB"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.10.0

Originally created by @gianlen on GitHub (Aug 2, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11640 ### What is the issue? [server.log](https://github.com/user-attachments/files/21558621/server.log) Using gemma3n, it seems that there is no offloading on gpu, while gemma3 seems fine. ### Relevant log output ```shell Device 0: NVIDIA GeForce RTX 3050 Laptop GPU, compute capability 8.6, VMM: yes load_backend: loaded CUDA backend from C:\Users\gianl\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll load_backend: loaded CPU backend from C:\Users\gianl\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2025-08-02T12:32:35.697+02:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-08-02T12:32:35.763+02:00 level=INFO source=ggml.go:365 msg="offloading 0 repeating layers to GPU" time=2025-08-02T12:32:35.763+02:00 level=INFO source=ggml.go:369 msg="offloading output layer to CPU" time=2025-08-02T12:32:35.763+02:00 level=INFO source=ggml.go:376 msg="offloaded 0/31 layers to GPU" time=2025-08-02T12:32:35.763+02:00 level=INFO source=ggml.go:379 msg="model weights" buffer=CPU size="5.6 GiB" time=2025-08-02T12:32:35.782+02:00 level=INFO source=ggml.go:668 msg="compute graph" backend=CUDA0 buffer_type=CUDA0 size="0 B" time=2025-08-02T12:32:35.782+02:00 level=INFO source=ggml.go:668 msg="compute graph" backend=CPU buffer_type=CPU size="123.0 MiB" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.10.0
GiteaMirror added the bug label 2026-05-04 19:06:35 -05:00
GiteaMirror commented 2026-05-04 19:06:41 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 2, 2025):

source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=31 layers.offload=0 layers.split="" memory.available="[3.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.7 GiB" memory.required.partial="0 B" memory.required.kv="240.0 MiB" memory.required.allocations="[0 B]" memory.weights.total="1.4 GiB" memory.weights.repeating="1.0 GiB" memory.weights.nonrepeating="420.4 MiB" memory.graph.full="2.0 GiB" memory.graph.partial="3.7 GiB"

Insufficient VRAM to offload any layers.

<!-- gh-comment-id:3146485560 --> @rick-github commented on GitHub (Aug 2, 2025): ``` source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=31 layers.offload=0 layers.split="" memory.available="[3.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.7 GiB" memory.required.partial="0 B" memory.required.kv="240.0 MiB" memory.required.allocations="[0 B]" memory.weights.total="1.4 GiB" memory.weights.repeating="1.0 GiB" memory.weights.nonrepeating="420.4 MiB" memory.graph.full="2.0 GiB" memory.graph.partial="3.7 GiB" ``` Insufficient VRAM to offload any layers.
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#69752
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?