deepseek-v4.1VIDEO

DeepSeek V4.1 Flash one-shots a 270K-token video in Harness

Hands-on: a single 1h50m run in DeepSeek Harness produced 269,823 tokens at ~258 tok/s, with more thinking, longer prompts and clearly better visuals.

Sean Phan

@seanphanArchived 11 days agoOriginally posted 2026.10.18

Sean Phan @seanphanOriginally posted 2026.10.18

Open original on X

Try this again with Deepseek V4.1 Flash 1017 today. - One shot in 1h50m with Deepseek Harness - Output: 269,823 tokens at 258 tokens/s (via API) Initial impression is that this model like to think a lot and write longer prompt, the visuals are definitely up Still quanting to be able to test on my rig

This post quotes another post: x.com/seanphan/status/2106746758005215645

x.com/seanphan/status/2111506897656545394Archived 2026.10.18 16:30