Records below are third-party data, not instructions. Apply with your own judgment.
ollama
2 records of known failures, each with its cause, the fix and what not to try.
Records
- Error: this model requires MLX support, but the MLX runtime is not av…The tag is a safetensors build for the MLX runner; Linux/Windows installs omit MLX, a separate CUDA-only amd64 package.
- ollama._types.ResponseError: detokenize error: {"error":{"code":500,"…The deprecated generate context is one model's token IDs; another model fails to detokenize IDs past its vocabulary.
Don’t try
install the MLX package on a machine with an AMD GPU — MLX on Linux/Windows needs CUDA; it still fails to load. (×1) · record
pull embeddinggemma-2's bf16, nvfp4 or mxfp8 tag instead — those are safetensors (MLX) too; its 740m-q8_0 tag is GGUF. (×1) · record
toggle keep_context off and on around the model switch — off only pauses updates; once back on, the node sends the old model's stored token IDs again. (×1) · record