deepseek-v4.1POST

DeepSeek V4.1 Flash 1017 GGUF quants: Q4_K_M ~445GB, Q3 fits four DGX Sparks

GGUF quants are out: Q2_K ~265GB, Q3_K_M ~350GB, Q4_K_M ~445GB, with Q3 fitting on four DGX Sparks; text-only for now and requires the llama.cpp V4.1 PR branch, plus a ~115GB single-Spark VQ build in progress.

𝙒𝙞𝙡𝙘𝙤 𝘷𝘢𝘯 𝘽𝙤𝙭𝙩𝙚𝙡 ⚡🚀🧲🌞

@nuonrgArchived 10 days agoOriginally posted 2026.10.17

𝙒𝙞𝙡𝙘𝙤 𝘷𝘢𝘯 𝘽𝙤𝙭𝙩𝙚𝙡 ⚡🚀🧲🌞 @nuonrgOriginally posted 2026.10.17

Open original on X

GGUF quants of DeepSeek V4.1 Flash 1017 are already up: Q2_K ~265GB, Q3_K_M ~350GB, Q4_K_M ~445GB. Q3 fits nicely on 4 DGX Sparks. Text-only for now, and you need the llama.cpp V4.1 PR branch. Even more interesting: a VQ build sized for a single Spark (~115GB) is being converted right now, with the Engram tables read from disk. One Spark, near-frontier open model. Links below.

x.com/nuonrg/status/2111408049411723352Archived 2026.10.18 16:45