Linked List
login
sign up
DeepSeek V4.1 Flash 1017 (max) - Intelligence, Performance & Price Analysis
artificialanalysis.ai
· first added by
@jdorsey
saved by
1 person
discussions
·
1
DeepSeek V4.1 Flash 1017 (Max)
190 pts · 96 comments · Oct 2026
190 pts · 96 comments · Oct 2026
▲
0
0 people saved or upvoted this
from the discussion
·
5
Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s
github.com
github.com
▲
2
2 people saved or upvoted this
lxe/dsx: DeepSeek-V4.1-Flash-1017 (552B MoE) on 2x RTX 3090 + 128 GB RAM: Rust + CUDA engine and 2-bit quant. 30-37 tok/s decode.
github.com
github.com
▲
0
0 people saved or upvoted this
The plunging price of thought
epoch.ai
epoch.ai
▲
0
0 people saved or upvoted this
Deepseek V4.1 Flash 1017 Max on Three.js
threejseval.com
threejseval.com
▲
0
0 people saved or upvoted this
DeepSeek V4.1 Flash 1017 API - Demo
deepinfra.com
deepinfra.com
▲
0
0 people saved or upvoted this
Feed
Explore
Sign In