Promethevs: Full DeepSeek-v4.1-Flash-1017, locally, on 12GB of VRAM
ar-nelson
13 points
5 comments
November 06, 2026
Related Discussions
Found 5 related stories in 167.2ms across 11,878 title embeddings via pgvector HNSW
- DeepSeek-v4-flash-vision-exp dares2573 · 473 pts · August 21, 2026 · 61% similar
- DeepSeek-v4.1-Exp nil1511 · 20 pts · September 10, 2026 · 61% similar
- DeepSeek-v4.1-Flash-1017 theykk · 790 pts · October 17, 2026 · 61% similar
- DeepSeek-V4-Flash-Vision-Exp amulyabaral · 20 pts · August 31, 2026 · 61% similar
- DeepSeek V4.1 Flash 1017 (Max) theanonymousone · 72 pts · October 19, 2026 · 60% similar
Discussion Highlights (1 comments)
rvz
If you were wondering: > Up to 7.4 tokens/s. It's not really "Flash" if it is 7 tokens per second. Also don't bother with any GPU lower than an RTX 5080 or even a DGX Spark (it is a scam) if you are seriously considering running frontier local models.