Running DeepSeek on a VPS on the Cheap
Thionne_WTZ · x · 2026-07-12
The post outlines a nearly free deployment strategy: running DeepSeek Flash on a VPS alongside Hermes.
To highlight the cost advantages, the author contrasts this with the hypothetical cost of running 20 亿 token on Opus 4.8. The core idea is to drive inference costs down drastically through lightweight deployments and model combinations.
More from Infra
- Gritt raises a new round to automate solar array installation and maintenance — rebeccakaden · 2026-07-21
- Refactoring 150k LOC Takes 96 Hours: Is Compute the Bottleneck for AI Coding? — robleclerc · 2026-07-21
- Seeking Recommendations: Essential Local Small Models (Audio/Vision/TTS) — DeepOrangeSky · 2026-07-21
- Compute Allocation Limits: The Root Cause of Missing Architecture Innovation in European LLMs — IgorCarron · 2026-07-21
- AI Energy Footprint Pales Compared to Transport and Agriculture — dreamwieber · 2026-07-21
- SkyPilot comes out of stealth with claims of 10x faster AI time-to-intelligence — songhan_mit · 2026-07-21