WHAT NEW IN X10.30 FRI

AI collections from X · 22 collections · 61,986 posts

deepseek-v4.1POST

Ollama Cloud test: DeepSeek V4.1 Flash sustains ~220 tok/s with 0.25–0.6s TTFT

Running deepseek-v4.1-flash:1017 on Ollama Cloud gave about 220 output tok/s sustained and a 0.25–0.6 second time to first token.

Surg Lt (Dr) Anan Jaiswal (Retd)
@docjaisArchived 12 days agoOriginally posted 2026.10.18
Surg Lt (Dr) Anan Jaiswal (Retd) @docjaisOriginally posted 2026.10.18
Open original on X

Benchmarked deepseek-v4.1-flash:1017 on Ollama Cloud. ~220 output tok/s sustained. TTFT 0.25 to 0.6s. Amazing 😍 @ollama

This post quotes another post: “Ollama adds DeepSeek-V4.1-Flash-1017 cloud with Claude Code and OpenCode launch commands”

x.com/docjais/status/2111653170632114484Archived 2026.10.18 16:44