Strata runs DeepSeek on a 2021 gaming GPU by paging model weights off your SSD
alex_verem · x · 2026-11-08
Strata is a free, open-source desktop app (Windows/Mac/Linux) that lets you download and chat with big AI models locally, no account required.
The clever part is memory management: when a model like DeepSeek doesn't fit in RAM/VRAM, Strata pages the overflowing weights straight off your SSD. The author demos running DeepSeek on a 2021 gaming GPU, showing how low the bar for local LLM deployment can go. Note the post doubles as promotion for the author's newsletter.
Related event: Open-source Strata runs DeepSeek locally on an RTX 3060 at 9-11 tokens/s(2 posts)→
More from Infra
- ResearchBoost Agent speeds up real research workloads 2.51x on average across 12 tasks — YouJiacheng · 2026-11-08
- Dev builds Cray-2 emulator from scratch, runs a GPT-3-class LLM at 1 token per 4s — inductionheads · 2026-11-08
- Hyperbolic CEO on compute market-making: bridging 3-year contracts and 3-week needs — YiMaTweets · 2026-11-08
- Ben Bajarin mocks 'we don't need data centers' take: CSPs were 'useless' too — BenBajarin · 2026-11-08
- KV Cache Quantization Tested Across 35 Quants: 8-bit Is Essentially Free for Qwen3.8 27B — Hefty_Wolverine_553 · 2026-11-08
- Developer burns $4,600 on rented GPUs with zero training steps, finishes same RL run on Tinker for under $100 — simonguozirui · 2026-11-08