Old Zhang's AI Learning
Oct 29, 2026 · Artificial Intelligence
Running DeepSeek-V4.1-Flash on Consumer GPUs: Strata's Tiered Offloading Fits 500GB MoE into 12GB VRAM
Strata inference engine enables local deployment of DeepSeek-V4.1-Flash on consumer GPUs by tiering model weights across VRAM, system RAM, and NVMe storage, achieving 9–11 tokens/s on an RTX 3060 12GB with 46GB RAM using 2-bit quantization and speculative decoding.
DeepSeek-V4.1-FlashMoEStrata
0 likes · 9 min read