[GH-ISSUE #15516] ollama not using gpu windows #56429

Open
opened 2026-04-29 10:49:01 -05:00 by GiteaMirror · 4 comments
Owner

Originally created by @athuljayaram on GitHub (Apr 12, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15516

What is the issue?

i have 8gb vram gpu
i observed even smallest models are not using gpu
can you provide setup for gpu or add a paramter to force gpu only

PS C:\Users\gamer> ollama ls
NAME ID SIZE MODIFIED
qwen3:4b 359d7dd4bcda 2.5 GB 7 minutes ago
gemma4:e2b 7fbdbf8f5e45 7.2 GB 22 minutes ago

PS C:\Users\gamer> ollama ps
NAME ID SIZE PROCESSOR CONTEXT UNTIL
qwen3:4b 359d7dd4bcda 41 GB 100% CPU 262144 4 minutes from now

PS C:\Users\gamer> nvidia-smi
Sun Apr 12 12:54:38 2026
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 595.97 Driver Version: 595.97 CUDA Version: 13.2 |
+-----------------------------------------+------------------------+----------------------+
| GPU Name Driver-Model | 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 5060 ... WDDM | 00000000:64:00.0 On | N/A |
| N/A 57C P5 8W / 105W | 1865MiB / 8151MiB | 10% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------

Relevant log output


OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @athuljayaram on GitHub (Apr 12, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15516 ### What is the issue? i have 8gb vram gpu i observed even smallest models are not using gpu can you provide setup for gpu or add a paramter to force gpu only PS C:\Users\gamer> ollama ls NAME ID SIZE MODIFIED qwen3:4b 359d7dd4bcda 2.5 GB 7 minutes ago gemma4:e2b 7fbdbf8f5e45 7.2 GB 22 minutes ago PS C:\Users\gamer> ollama ps NAME ID SIZE PROCESSOR CONTEXT UNTIL qwen3:4b 359d7dd4bcda 41 GB 100% CPU 262144 4 minutes from now PS C:\Users\gamer> nvidia-smi Sun Apr 12 12:54:38 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 595.97 Driver Version: 595.97 CUDA Version: 13.2 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Driver-Model | 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 5060 ... WDDM | 00000000:64:00.0 On | N/A | | N/A 57C P5 8W / 105W | 1865MiB / 8151MiB | 10% Default | | | | N/A | +-----------------------------------------+------------------------+---------------------- ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-29 10:49:01 -05:00
Author
Owner

@rick-github commented on GitHub (Apr 12, 2026):

Reduce context length.

<!-- gh-comment-id:4231478343 --> @rick-github commented on GitHub (Apr 12, 2026): Reduce [context length](https://docs.ollama.com/context-length).
Author
Owner

@athuljayaram commented on GitHub (Apr 12, 2026):

tried with another cli tool, works fine, even increased context length. still working.

<!-- gh-comment-id:4231724000 --> @athuljayaram commented on GitHub (Apr 12, 2026): tried with another cli tool, works fine, even increased context length. still working.
Author
Owner

@rick-github commented on GitHub (Apr 12, 2026):

Server logs will aid in debugging.

<!-- gh-comment-id:4231740691 --> @rick-github commented on GitHub (Apr 12, 2026): [Server logs](https://docs.ollama.com/troubleshooting) will aid in debugging.
Author
Owner

@PureBlissAK commented on GitHub (Apr 18, 2026):

🤖 Automated Triage & Analysis Report

Issue: #15516
Analyzed: 2026-04-18T18:20:46.120203

Analysis

  • Type: unknown
  • Severity: medium
  • Components: unknown

Implementation Plan

  • Effort: medium
  • Steps:

This issue has been triaged and marked for implementation.

<!-- gh-comment-id:4274307141 --> @PureBlissAK commented on GitHub (Apr 18, 2026): <!-- ollama-issue-orchestrator:v1 issue:15516 --> ## 🤖 Automated Triage & Analysis Report **Issue**: #15516 **Analyzed**: 2026-04-18T18:20:46.120203 ### Analysis - **Type**: unknown - **Severity**: medium - **Components**: unknown ### Implementation Plan - **Effort**: medium - **Steps**: *This issue has been triaged and marked for implementation.*
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#56429