deepseek-v4.1POST

DeepSeek V4.1 Flash runs locally on a 64GB RAM dev desktop

A user runs V4.1 Flash on an ordinary 64GB-RAM dev desktop using Strata plus gsq-rco quants, arguing that shrinking open weights make per-token mid-tier pricing harder to justify.

Rudra Satani

@rudraxx13Archived 6 days agoOriginally posted 2026.10.24

Rudra Satani @rudraxx13Originally posted 2026.10.24

Open original on X

deepseek v4.1 flash running on 64gb of ram now, through strata + gsq-rco quants from @mhelcig that's a normal-ish dev desktop, not a server every time open weights get this small, paying per token for the mid tier gets harder to justify

This post quotes another post: “DeepSeek V4.1 Flash runs on 64GB RAM via Strata and GSQ-RCO quants”

x.com/rudraxx13/status/2114023909297455264Archived 2026.10.25 12:02