'Buy 4 Mac Studios and run a 1T model' instead of paying half your salary on tokens
yuxiangw_cs · x · 2026-09-30
Dimitris Papail argues that paying half your salary on tokens makes little sense when you can buy 4 Mac Studios and run a 1T-parameter model locally instead. Researcher yuxiangwcs agrees, adding that this is yet another reason to thank open-weight models — open weights are what make such local deployments of large models viable.
Related event: Professor: 4 Mac Studios running a 1T model beats burning salary on tokens(3 posts)→
More from Infra
- PyTorchCon NA puts vLLM center stage: KV cache, disaggregated serving, expert parallelism — PyTorch · 2026-09-30
- Oxmiq Open-Sources NVFP4 Quantized Hy4 Model, Runs on RTX 6000 Pro — RajaXg · 2026-09-30
- Inference Engineering Without a GPU: Engineer Details a CPU-First Path into the Field — abhijithneil · 2026-09-30
- Anthropic carries $252B in non-cancelable compute obligations plus $161.2B in Broadcom TPU leases — ns123abc · 2026-09-30
- Datacenter backlash accelerating: indexed YouTube videos up 4.8x in 30 days — zealcaiden · 2026-09-30
- Blackstone, KKR, Apollo put $5.3B into gas plants powering AI data centers — pstAsiatech · 2026-09-30