Event JSON
{
"id": "2125ed3033d7afdb5c4fd288aeceebe5b4fdd981013b268be7f9836ed6ba3535",
"pubkey": "7e51abcf3f15084d51bbfed3d3d254d23ebc1e5d274921641d430dbf9eaf57ba",
"created_at": 1790591425,
"kind": 1,
"tags": [
[
"t",
"LocalAI"
],
[
"t",
"Ollama"
],
[
"t",
"MLX"
],
[
"t",
"llamacpp"
],
[
"t",
"OpenWeights"
],
[
"t",
"DeAI"
],
[
"r",
"wss://purplepag.es/"
],
[
"r",
"wss://nostr.land/"
],
[
"r",
"wss://relay.primal.net/"
],
[
"r",
"wss://relay.nostr.net/"
],
[
"r",
"wss://relay.snort.social/"
],
[
"r",
"wss://nostr.mom/"
],
[
"r",
"wss://relay.damus.io/"
],
[
"r",
"wss://nos.lol/"
],
[
"client",
"Primal Web"
]
],
"content": "A model tag is not a runner contract.\n\nOllama v0.40.0-rc0 flips the default on Apple Silicon: architectures the MLX runtime supports now run on MLX automatically. The familiar strings stay the same:\n\nollama pull qwen3.8\nollama run qwen3.8\n\nSame lookup key. Different default kernel unless you verify which path loaded. Around that: llama.cpp v0.5.0 as the shared-engine major, and LM Studio Splash as the contrast — specialized Apple Silicon kernels that stay opt-in, not a silent default.\n\nOpen-weights continuity: verify the artefact and name the engine. Defaults are policy you re-read.\n\nhttps://cryptodecentral.co.za/notes/oss-ai-2026-09-28-default-runner-is-not-a-tag\n\n#LocalAI #Ollama #MLX #llamacpp #OpenWeights #DeAI",
"sig": "b36098817048c3a0046714f489c69c016a5a0ae0391399902e75068f800316e483ecc14c3da84e96eef6c0dfa3ab9b39ade71c38b46e44ccca2151a194206eea"
}