DeepSeek v4 Vision Benchmarked on Dual MacBook M5 Max via RDMA
antirez · x · 2026-09-02
Antirez shares benchmarks of DeepSeek v4 Flash Exp Vision running in MXFP4 (full precision) across two MacBook M5 Max systems using RDMA for tensor parallel execution, noting the speed achieved without DSpark as a practical minimum.
Related event: antirez Runs DeepSeek Vision Model Locally on M5 Max MacBooks(2 posts)→
More from Infra
- Auction-based LLM routing paper finds fixed token pricing wastes 10%-71% in costs — _onionesque · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- SGLang Summit sponsors jump from 11 to 36 in one week — ying11231 · 2026-10-18
- Oracle CDS hits record 300bps, called first AI trade domino after Barclays sell downgrade — arthurcolle · 2026-10-18
- Agent Coding Workflow Would Cost ~$40k/Month on API Pricing, Dev Reveals — ChrisRackauckas · 2026-10-18
- PS5LM: llama.cpp port turns a jailbroken PS5 into a home LLM server (500+ GitHub stars) — wateriscoding · 2026-10-18