IST Austria 的 Strata 量化让 763B V4.1 Flash 跑在 12GB 显卡上，约 5–10

Rexei @iamrexei原推发布于 2026.10.25

在 X 上打开原推

763B DEEPSEEK ON A 12GB GPU? HOLY SH*T researchers at IST Austria released a heavily quantized DeepSeek-V4.1-Flash. Strata can run it on a single 12GB GPU by keeping most of the model in RAM and reading the rest from an SSD ▸ RTX 5070 + 64GB RAM: about 5 output tokens/s ▸ RTX 3060 + 46GB RAM: about 8–10 output tokens/s in a separate test ▸ you still need 239GB of disk for the smallest package, or 257GB for the tested 2-bit version → “runs on 12GB VRAM” does not mean “fits in 12GB.” this is an impressive local run, but i wouldn't call it a fast setup for coding agents yet links in first reply ↓