Q: How fast is DeepSeek-V4.1-Flash on the AMD Radeon RX 6700 10GB (non-XT)?

~5.7–9.1 tok/s (active-expert estimate) on the AMD Radeon RX 6700 10GB (non-XT). computed roofline: 320 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

Question 1

Can the AMD Radeon RX 6700 10GB (non-XT) run DeepSeek-V4.1-Flash?

Accepted Answer

DeepSeek-V4.1-Flash needs about 170.9GB working set (weights 168.9GB + KV cache 2GB at 4k context). The AMD Radeon RX 6700 10GB (non-XT) offers ~10GB usable — verdict: no. 170.9 GB vs 10 GB usable — does not fit

Question 2

How fast is DeepSeek-V4.1-Flash on the AMD Radeon RX 6700 10GB (non-XT)?

Accepted Answer

~5.7–9.1 tok/s (active-expert estimate)

computed roofline: 320 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

Question 3

What should I run DeepSeek-V4.1-Flash on instead?

Accepted Answer

ASUS ExpertCenter Pro ET900N G3 (GB300) runs it fully ($60000).

Can the AMD Radeon RX 6700 10GB (non-XT) run DeepSeek-V4.1-Flash?

Run DeepSeek-V4.1-Flash on instead