time=2026-03-26T09:06:53.911-07:00 level=INFO source=routes.go:1728 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:INFO OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/daniel/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2026-03-26T09:06:53.911-07:00 level=INFO source=routes.go:1730 msg="Ollama cloud disabled: false" time=2026-03-26T09:06:53.912-07:00 level=INFO source=images.go:477 msg="total blobs: 21" time=2026-03-26T09:06:53.912-07:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0" [GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached. [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production. - using env: export GIN_MODE=release - using code: gin.SetMode(gin.ReleaseMode) [GIN-debug] HEAD / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers) [GIN-debug] GET / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers) [GIN-debug] HEAD /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func3 (5 handlers) [GIN-debug] GET /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func4 (5 handlers) [GIN-debug] GET /api/status --> github.com/ollama/ollama/server.(*Server).StatusHandler-fm (5 handlers) [GIN-debug] POST /api/pull --> github.com/ollama/ollama/server.(*Server).PullHandler-fm (5 handlers) [GIN-debug] POST /api/push --> github.com/ollama/ollama/server.(*Server).PushHandler-fm (5 handlers) [GIN-debug] HEAD /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers) [GIN-debug] GET /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers) [GIN-debug] POST /api/show --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (5 handlers) [GIN-debug] DELETE /api/delete --> github.com/ollama/ollama/server.(*Server).DeleteHandler-fm (5 handlers) [GIN-debug] POST /api/me --> github.com/ollama/ollama/server.(*Server).WhoamiHandler-fm (5 handlers) [GIN-debug] POST /api/signout --> github.com/ollama/ollama/server.(*Server).SignoutHandler-fm (5 handlers) [GIN-debug] DELETE /api/user/keys/:encodedKey --> github.com/ollama/ollama/server.(*Server).SignoutHandler-fm (5 handlers) [GIN-debug] POST /api/create --> github.com/ollama/ollama/server.(*Server).CreateHandler-fm (5 handlers) [GIN-debug] POST /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers) [GIN-debug] HEAD /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers) [GIN-debug] POST /api/copy --> github.com/ollama/ollama/server.(*Server).CopyHandler-fm (5 handlers) [GIN-debug] POST /api/experimental/web_search --> github.com/ollama/ollama/server.(*Server).WebSearchExperimentalHandler-fm (5 handlers) [GIN-debug] POST /api/experimental/web_fetch --> github.com/ollama/ollama/server.(*Server).WebFetchExperimentalHandler-fm (5 handlers) [GIN-debug] GET /api/ps --> github.com/ollama/ollama/server.(*Server).PsHandler-fm (5 handlers) [GIN-debug] POST /api/generate --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (5 handlers) [GIN-debug] POST /api/chat --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (5 handlers) [GIN-debug] POST /api/embed --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (5 handlers) [GIN-debug] POST /api/embeddings --> github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers) [GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (7 handlers) [GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (7 handlers) [GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (7 handlers) [GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers) [GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (7 handlers) [GIN-debug] POST /v1/responses --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (7 handlers) [GIN-debug] POST /v1/images/generations --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (7 handlers) [GIN-debug] POST /v1/images/edits --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (7 handlers) [GIN-debug] POST /v1/messages --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (7 handlers) time=2026-03-26T09:06:53.912-07:00 level=INFO source=routes.go:1786 msg="Listening on 127.0.0.1:11434 (version 0.0.0)" time=2026-03-26T09:06:53.912-07:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-03-26T09:06:53.913-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="/Storage/Projects/ML-LLMs-and-CUDA/ollama.git/ollama runner --ollama-engine --port 37971" time=2026-03-26T09:06:54.270-07:00 level=INFO source=server.go:432 msg="starting runner" cmd="/Storage/Projects/ML-LLMs-and-CUDA/ollama.git/ollama runner --ollama-engine --port 45069" time=2026-03-26T09:06:54.647-07:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-318afd82-d7c1-4842-ef91-607d09d6f7f3 filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3060 Laptop GPU" libdirs=ollama driver=13.2 pci_id=0000:01:00.0 type=discrete total="6.0 GiB" available="5.4 GiB" time=2026-03-26T09:06:54.647-07:00 level=INFO source=types.go:42 msg="inference compute" id=8680609a-0100-0000-0002-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) UHD Graphics (TGL GT1)" libdirs=ollama driver=0.0 pci_id=0000:00:02.0 type=iGPU total="46.9 GiB" available="42.2 GiB" time=2026-03-26T09:06:54.647-07:00 level=INFO source=routes.go:1836 msg="vram-based default context" total_vram="52.9 GiB" default_num_ctx=262144