Local AI Daily: DeepSeek-V4.1-Flash hits 65.7 tok/s on M5 Ultra, TensorFold cuts agent TTFT 34x
AIFlow_ML · x · 2026-11-11
Local AI Daily (Nov 11) rounds up local inference news with source-labeled numbers (MEASURED / VENDOR-CLAIM / ESTIMATE): TensorFold 1.2.6 ships a prompt cache for many concurrent agents, claiming median follow-up TTFT drops from 546 s to 15.9 s on M3 Ultra and 105 s to 25.8 s on GB10; a Mac Studio M5 Ultra 512 GB runs official MIT-licensed DeepSeek-V4.1-Flash at 65.7 tok/s on a 128K prompt. Plus GLM-5.3-Flash on a single Spark, DSpine field data, and a hype check on a 700 tok/s 5090 claim.
More from Infra
- PufferLib: open-source RL library trains 60M samples/sec on one GPU — jsuarez · 2026-11-11
- Rise of ASICs may erode NVIDIA's CUDA moat, commentator argues — bookwormengr · 2026-11-11
- Fable 5.2 tops SemiAnalysis' GDPx chip design leaderboard at 16.4%, but some tasks saw no gains — ycombinator · 2026-11-11
- Tencent's newest flagship Hy4 goes live, co-served by Inferact with open-weight preview — VoidAsuka · 2026-11-11
- Claude ported itself to AMD MI355X in ~3 days, work that took dozens of engineers 6-12 months — AnushElangovan · 2026-11-11
- Analyst: AI datacenter demand will eventually be built in space — TinfoilTricorn · 2026-11-11