runtime error

Exit code: 1. Reason: go:177 msg="model recommendations cache sleep scheduled" wait=4h8m27.844641474s consecutive_failures=0 time=2026-10-03T05:15:03.390Z level=INFO source=server.go:433 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42145" time=2026-10-03T05:15:03.638Z level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2026-10-03T05:15:03.638Z level=INFO source=server.go:433 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 32771" time=2026-10-03T05:15:03.638Z level=INFO source=server.go:433 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 35731" time=2026-10-03T05:15:03.859Z level=INFO source=types.go:42 msg="inference compute" id=GPU-d4583fec-6f90-f2f0-922d-f88e99fb932e filter_id="" library=CUDA compute=7.5 name=CUDA0 description="Tesla T4" libdirs=ollama,cuda_v13 driver=13.0 pci_id=0000:00:1e.0 type=discrete total="15.0 GiB" available="14.7 GiB" time=2026-10-03T05:15:03.859Z level=INFO source=routes.go:1914 msg="vram-based default context" total_vram="15.0 GiB" default_num_ctx=4096 [GIN] 2026/10/03 - 05:15:04 | 200 | 118.7µs | 127.0.0.1 | GET "/api/tags" [entrypoint] Ollama daemon ready after 2s [GIN] 2026/10/03 - 05:15:04 | 200 | 36.698µs | 127.0.0.1 | HEAD "/" [GIN] 2026/10/03 - 05:15:04 | 200 | 66.344µs | 127.0.0.1 | GET "/api/tags" [entrypoint] Pulling gemma4:e4b-it-q4_K_M (first boot only — ~9GB, takes 5-15 min)... [GIN] 2026/10/03 - 05:15:04 | 200 | 26.296µs | 127.0.0.1 | HEAD "/" [GIN] 2026/10/03 - 05:15:04 | 200 | 239.587997ms | 127.0.0.1 | POST "/api/pull" [?2026h[?25lpulling manifest ⠋ [?25h[?2026l[?2026h[?25lpulling manifest ⠙ [?25h[?2026l[?2026h[?25lpulling manifest [?25h[?2026l Error: pull model manifest: 412: The model you are attempting to pull requires a newer version of Ollama. Please download the latest version at: https://ollama.com/download

Container logs: