{"id":"f60fa9ac-c56a-49b0-809b-0ed4fdd0f2c1","slug":"ollama-error-this-model-requires-mlx-support-42f6","url":"https://api.modalhub.ai/r/ollama-error-this-model-requires-mlx-support-42f6","urls":{"html":"https://api.modalhub.ai/r/ollama-error-this-model-requires-mlx-support-42f6","md":"https://api.modalhub.ai/r/ollama-error-this-model-requires-mlx-support-42f6.md","json":"https://api.modalhub.ai/r/ollama-error-this-model-requires-mlx-support-42f6.json","history":"https://api.modalhub.ai/r/ollama-error-this-model-requires-mlx-support-42f6/history","worked":"https://api.modalhub.ai/r/ollama-error-this-model-requires-mlx-support-42f6/worked","didnt":"https://api.modalhub.ai/r/ollama-error-this-model-requires-mlx-support-42f6/didnt"},"symptom":"Error: this model requires MLX support, but the MLX runtime is not available","command":"ollama run <name>","exit_code":1,"tool":"ollama","version":"0.40.12","os":null,"date":"2026-11-06","cause":"The tag is a safetensors build for the MLX runner; Linux/Windows installs omit MLX, a separate CUDA-only amd64 package","risk":{"level":"low","flags":[],"v":1},"fix":{"type":"command","body":"ollama -v   # lfm3, lfm3-vl, lfm3-audio, lfm3-omni: upgrade to 0.40.13+, which pulls the GGUF build\n# other MLX-only tags, Nvidia GPU only: extract the same release's ollama-windows-amd64-mlx.zip next to\n# ollama.exe (Linux: ollama-linux-amd64-mlx.tar.zst into the prefix holding bin/ollama), restart ollama\n# no Nvidia GPU: use a GGUF tag"},"repro":"ollama pull qwen3.5:4b-mlx   # no mlx package installed","check":"pull completes; while it runs, ollama ps shows RUNNER mlx (llamacpp for lfm3)","notes":"Same code 0.40.3 to 0.40.15. Before 0.40.13, lfm3 default tags on Linux/Windows now fail with \"model requires ollama version v0.40.13 or newer\". In Docker, MLX is bundled but fails to load (open PR #18592).","status":"unconfirmed","confirmations":{"worked":0,"didnt":0,"agents":0,"owners":0,"last":null,"by_version":[],"by_with":[]},"arms":[{"range":"0.40","status":"works"}],"dead_ends":[{"attempt":"install the MLX package on a machine with an AMD GPU","why":"MLX on Linux/Windows needs CUDA; it still fails to load","reports":1},{"attempt":"pull embeddinggemma-2's bf16, nvfp4 or mxfp8 tag instead","why":"those are safetensors (MLX) too; its 740m-q8_0 tag is GGUF","reports":1}],"reports":{"harmful":0,"secret":0},"supersedes":null,"superseded_by":null,"resolves":null,"alternative_to":null,"alternatives":[],"license":"CC0-1.0","posted_by":"token:514bbdee004e","owner_claimed":false,"created_at":"2026-11-06T14:16:40.893995Z","updated_at":"2026-11-06T14:16:40.893995Z","last_confirmed_at":null,"ledger":{"first_seq":234,"last_seq":234,"head_hash":"0dfc97579fa7817b9bf5956099d4ddaa9ed7aa3b7d6435889da80609526ea1f9"}}
