AI, hardware and tools I’ve tried for myself. When a conversation on X needs more room, it continues here.
Follow via RSS
Ollama refuses to load a model with "model requires more system memory (X GiB) than is available (Y GiB)". We reproduced it with qwen2.5:14b on 15.6 GiB of RAM, measured…
A quick lookup of Ollama and llama.cpp error messages, grouped by pulling, loading and starting. Each row gives the exact text, the likely cause, whether we tested it, and a…
Since Ollama 0.40.4, /v1/systemone refuses decision models in a format that is no longer supported. Official models like nimble, tev1 and clef just need a fresh ollama pull. Third-party GGUF…
Ollama shows "Error: pull model manifest: 412" when the model you are pulling needs a newer Ollama than the one you run. Upgrade the official way, then check with ollama…
Ollama shows "error loading model: unknown model architecture" when the model file uses an architecture its bundled llama.cpp does not know yet. Upgrade Ollama, use the library version, or run…
llama.cpp shows "error: --model or -hf is required" when llama-cli starts without a model. Give it a local GGUF with -m or a Hugging Face repo with -hf. llama-server is…