Running a 510GB DeepSeek model on a 128GB DGX Spark by pruning unused MoE experts

pbaylies · x · 2026-09-14

@0xBakeer demonstrates running the 510GB DeepSeek-V4.1-Flash with 256k context and thinking mode on a single 128GB DGX Spark — no smaller model, no cloud.

The trick exploits MoE sparsity: each token activates only 6 of 384 experts, so he pre-selects which experts the target job needs and loads only those.

Original post →

More from Infra

Infra channel →