Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix [Bug]: RTX 5070 Ti not detected (Total VRAM: 0 B) - Compute Capability 12.0 / Blackwell Architecture [11 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#14960•Fetched 2026-04-08 01:03:56
View on GitHub
Comments
11
Participants
3
Timeline
13
Reactions
0
Author
Noct2visNoct2vis
Participants
Noct2visNoct2visrick-githubrick-githubviba1viba1
Timeline (top)
commented ×11closed ×1labeled ×1

Ollama version 0.18.1 fails to detect the newly released NVIDIA GeForce RTX 5070 Ti (12GB) on Windows. Even with CUDA Toolkit 13.2 installed and proper environment variables set, the server defaults to CPU and reports total_vram="0 B".

Error Message

time=2026-03-19T16:36:09.609Z level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-03-19T16:36:09.634Z level=DEBUG source=server.go:431 msg=subprocess CUDA_PATH="C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.2" OLLAMA_CUDA_VERSION=12 OLLAMA_DEBUG=1 OLLAMA_GPU_LAYERS=cuda OLLAMA_LLM_LIBRARY=cuda
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=102.1248ms
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=110.4689ms
time=2026-03-19T16:36:09.718Z level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu
time=2026-03-19T16:36:09.718Z level=INFO source=routes.go:1832 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096

Root Cause

Ollama version 0.18.1 fails to detect the newly released NVIDIA GeForce RTX 5070 Ti (12GB) on Windows. Even with CUDA Toolkit 13.2 installed and proper environment variables set, the server defaults to CPU and reports total_vram="0 B".

Code Example

time=2026-03-19T16:36:09.609Z level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-03-19T16:36:09.634Z level=DEBUG source=server.go:431 msg=subprocess CUDA_PATH="C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.2" OLLAMA_CUDA_VERSION=12 OLLAMA_DEBUG=1 OLLAMA_GPU_LAYERS=cuda OLLAMA_LLM_LIBRARY=cuda
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=102.1248ms
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=110.4689ms
time=2026-03-19T16:36:09.718Z level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu
time=2026-03-19T16:36:09.718Z level=INFO source=routes.go:1832 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096

### Relevant log output
RAW_BUFFERClick to expand / collapse

Description

Ollama version 0.18.1 fails to detect the newly released NVIDIA GeForce RTX 5070 Ti (12GB) on Windows. Even with CUDA Toolkit 13.2 installed and proper environment variables set, the server defaults to CPU and reports total_vram="0 B".

Environment

  • Ollama Version: 0.18.1 (Windows Native)
  • GPU: NVIDIA GeForce RTX 5070 Ti (12GB)
  • Architecture: Blackwell (Compute Capability 12.0)
  • OS: Windows 11
  • Driver Version: 58x.xx (Latest available for 50-series)
  • CUDA Toolkit: v13.2

Steps Taken to Troubleshoot

  1. Verified nvidia-smi correctly displays the GPU and CUDA version.
  2. Set OLLAMA_DEBUG=1 to capture detailed logs.
  3. Attempted to manually link CUDA 13.2 DLLs (renamed to *_12.dll) into the Ollama program directory to resolve library version mismatches.
  4. Set CUDA_VISIBLE_DEVICES=0 and OLLAMA_VULKAN=1, but the discovery still resulted in 0 B VRAM.
  5. Killed all background processes (ollama.exe, ollama_llama_server.exe) to ensure a clean start with ollama serve.

Logs

time=2026-03-19T16:36:09.609Z level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-03-19T16:36:09.634Z level=DEBUG source=server.go:431 msg=subprocess CUDA_PATH="C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.2" OLLAMA_CUDA_VERSION=12 OLLAMA_DEBUG=1 OLLAMA_GPU_LAYERS=cuda OLLAMA_LLM_LIBRARY=cuda
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=102.1248ms
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0
time=2026-03-19T16:36:09.718Z level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=110.4689ms
time=2026-03-19T16:36:09.718Z level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu
time=2026-03-19T16:36:09.718Z level=INFO source=routes.go:1832 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096

### Relevant log output

```shell

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.18.1

extent analysis

Fix Plan

To resolve the issue of Ollama failing to detect the NVIDIA GeForce RTX 5070 Ti (12GB) on Windows, follow these steps:

  • Update the Ollama configuration to include the latest CUDA toolkit path.
  • Ensure the OLLAMA_CUDA_VERSION environment variable is set to 13.2 to match the installed CUDA toolkit version.
  • Modify the Ollama startup script to include the --cuda-path flag pointing to the CUDA 13.2 installation directory.

Example code changes:

// Update the cudaPath variable to point to the CUDA 13.2 installation directory
cudaPath := "C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.2"

// Set the OLLAMA_CUDA_VERSION environment variable
os.Setenv("OLLAMA_CUDA_VERSION", "13.2")

// Update the Ollama startup script to include the --cuda-path flag
cmd := exec.Command("ollama", "serve", "--cuda-path", cudaPath)

Alternatively, you can also try setting the CUDA_PATH environment variable before starting Ollama:

set CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.2
ollama serve

Verification

To verify that the fix worked, check the Ollama logs for the presence of the GPU device and the correct VRAM allocation:

time=2026-03-19T16:36:09.718Z level=INFO source=types.go:60 msg="inference compute" id=gpu library=cuda compute="cuda" name="NVIDIA GeForce RTX 5070 Ti"
time=2026-03-19T16:36:09.718Z level=INFO source=routes.go:1832 msg="vram-based default context" total_vram="12 GB" default_num_ctx=4096

Extra Tips

  • Ensure that the CUDA toolkit version matches the version supported by the NVIDIA driver.
  • Verify that the nvidia-smi command correctly displays the GPU device and CUDA version.
  • If issues persist, try resetting the Ollama configuration and environment variables to their default values.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#installation#tensor shape#environment variable

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING