▲ local intelligence

can it run

Can the AMD Radeon RX 6900 XT run DeepSeek-V4.1-Flash?

NO

170.9 GB vs 16 GB usable — does not fit

16GB · RDNA2 · model file 168.9GB · 552B+196B Engram MoE

~9.1–15 tok/s (active-expert estimate)

computed roofline: 512 GB/s × 0.45–0.72 efficiency window / 25.3GB (Q4_K_M) — bands, never points.

MoE: file is 168.9GB (that decides fit) but only ~82.8B of experts activate per token (~25.3GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math

Run DeepSeek-V4.1-Flash on instead

→ ASUS ExpertCenter Pro ET900N G3 (GB300) — cheapest catalog machine that runs DeepSeek-V4.1-Flash fully ($60000)

→ rx-7900-xtx — the next step up from AMD Radeon RX 6900 XT

→ every model the AMD Radeon RX 6900 XT can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the AMD Radeon RX 6900 XT · fit = weights + 4k KV vs usable memory