35 lines
1.3 KiB
Markdown
35 lines
1.3 KiB
Markdown
|
---
|
||
|
|
type: xpost
|
||
|
|
source: https://x.com/ollama/status/2085975426321858799
|
||
|
|
author: ollama (offizieller Account)
|
||
|
|
date: 2026-08-08
|
||
|
|
topic: ollama-cloud, deepseek-v4-flash, performance, privacy
|
||
|
|
status: raw
|
||
|
|
---
|
||
|
|
|
||
|
|
# Ollama: DeepSeek-V4-Flash mit 200+ tps und Zero Data Retention
|
||
|
|
|
||
|
|
## Post (13h vor 2026-08-08)
|
||
|
|
|
||
|
|
> Currently serving 200 tps+ output speed for DeepSeek-V4-Flash on Ollama's cloud with zero data retention (ZDR). Have an amazing weekend 🫡
|
||
|
|
|
||
|
|
## Kontext (vorheriger Post, 13h davor)
|
||
|
|
|
||
|
|
> DeepSeek-V4-Flash-0731 is now fully rolled out as the new default for deepseek-v4-flash on Ollama's cloud.
|
||
|
|
> This model combines speed, efficiency, and frontier-level performance.
|
||
|
|
> Fast: 120+ output tps on Ollama's cloud
|
||
|
|
> Private: zero data retention hosting in US & Europe
|
||
|
|
|
||
|
|
## Kernaussagen
|
||
|
|
|
||
|
|
- **DeepSeek-V4-Flash-0731** ist neuer Default für `deepseek-v4-flash` auf Ollama Cloud
|
||
|
|
- **200+ tps** Output-Speed (im Folge-Post; der Rollout-Post nennt 120+ tps)
|
||
|
|
- **Zero Data Retention (ZDR)** — Hosting in US & Europa
|
||
|
|
- Kombination aus Speed, Effizienz und Frontier-Level-Performance
|
||
|
|
|
||
|
|
## Relevanz für Hector-Setup
|
||
|
|
|
||
|
|
- `ollama/deepseek-v4-flash:0731:cloud` ist unser aktuelles Tier-0-Modell (Heartbeat/Cron-Jobs)
|
||
|
|
- 200+ tps Output bestätigt die Eignung für schnelle, kostengünstige Status-/Script-Jobs
|
||
|
|
- ZDR (US/EU) relevant für Datenschutz-Betrachtung bei Cloud-Inferenz
|