← All templates

Ollama runtime (CUDA)

Published, not hardware-testedollama

Operator-approved runtime configuration, not GPU-tested.

Needs 8 GiB VRAM · CUDA on NVIDIA

No GPU big enough is free right now.

New machines appear as hosts connect them.

No speed benchmarks yet, so we match on price.

Template details
Rating
No ratings yet
Runs
0
Min VRAM
8.6 GB
Backend
CUDA · NVIDIA GPUs
Version
ollama-cuda-v1.0.0
Image digest
dc4c3479f907…
Health check
SSH probe on the leased endpoint

Operator-approved runtime configuration, not GPU-tested. Requires a profile allowing port 8000 and a private authenticated rental access path. Model downloads consume /work storage and require their own license review. Source: https://github.com/ollama/ollama (0.34.0). License: MIT, https://github.com/ollama/ollama/blob/main/LICENSE; model licenses remain separate.

We match GPUs on their measured runtime and dedicated VRAM. A hardware report doesn't qualify another vendor's backend.

Reported on real GPUs

People report these themselves. We haven't checked them.

No reports yet.

Sign in to report how this template runs on your GPU.

Reviews

No reviews yet.

Sign in to leave a review.