Local Ai
By end of next year. End of year after for 16gb vram. Do folk really need more for most things? Not really. But just call the cloud models w…
By end of next year. End of year after for 16gb vram. Do folk really need more for most things? Not really. But just call the cloud models when you do. What's a reasonable timeline for a GPT 5.4/Opus
By end of next year. End of year after for 16gb vram. Do folk really need more for most things? Not really. But just call the cloud models when you do. What's a reasonable timeline for a GPT 5.4/Opus 4.6 level LLM that runs locally on a good Macbook 10 years? much less? much more?
Related
- @hwchase17 I think harness/managed agents is a way for Anthropic to keep its Moat. As models get mature, the need for cloud LLMs might reduc…
- How much more useage do you get from a $20 pro plan when using cloud models? Or OpenRouter better??
- @openclaw And of course @Ollama for the local model-serving engine. 🦙
Source: Emad Mostaque (X) | 2026-04-23