A $6,000 rig to run full, non-distilled DeepSeek-R1 locally
carrigmat · x · 2026-08-27
Developer carrigmat corrects an earlier link to a complete hardware + software setup for running Deepseek-R1 locally — the actual model, no distillations, with Q8 quantization for full quality, at a total cost of $6,000, with all download and part links included.
With the full 16-drive array, he claims the system would even be ready for the 10T-parameter models of 2027.
More from Infra
- Grokpute launches distributed GPU training network — jw2yang4ai · 2026-08-27
- Weaviate ships query profiling: one flag pinpoints slow-query bottlenecks inline — victorialslocum · 2026-08-27
- Storage architecture for AI sandboxes: Local root + S3 — aniketmaurya · 2026-08-27
- Weaviate adds 'effort' parameter to tune search quality vs. compute cost — CShorten30 · 2026-08-27
- Managing Token Spend in Multi-Agent Setups — souvlakee · 2026-08-27
- Organizations Spend Over $117k Monthly on Agentic AI Inference — perilli · 2026-08-27