antirez: DwarfStar Runs DeepSeek v4 Flash and GLM 5.2 Tensor Parallel on Two MacBooks via RDMA
antirez · x · 2026-07-07
Redis creator antirez announces that on DwarfStar, using RDMA, tensor parallelism was achieved on two M5Max 128GB MacBooks, successfully running DeepSeek v4 Flash and GLM 5.2.
Particularly significant for GLM: previously no single commercially available machine could fully fit the model in GPU memory, now cross-machine tensor parallelism enables it, an engineering breakthrough for local/edge deployment of frontier open-source models.
More from Infra
- Analyst: Ant has the most fungible AI workload of any model provider today — BenBajarin · 2026-10-26
- Anthropic S-1: training infra edge cut per-task cost 40% and doubled revenue growth — BenBajarin · 2026-10-26
- Rewriting scaling law study: optimal synthetic data share rises from 10% to 32% with compute — heghbalz · 2026-10-26
- US states halt new data centers as 72% of Americans oppose local builds — YvesMulkers · 2026-10-26
- $5M Seed Round Can't Afford One DeepSeek Training Run: GPU-less AI Startup's Three Paths — FinanceYF5 · 2026-10-26
- HBM demand shifts: low-stack inference plans shelved, Rubin to go 12-high only — BenBajarin · 2026-10-26