Ollama US hosting coming soon, bringing DeepSeek-V4.1-Flash-1017 stateside
gaganghotra_ · x · 2026-10-18
Ollama announced it is working on getting its US hosts up and running, with gaganghotra noting DeepSeek-V4.1-Flash-1017 will soon be served from US-hosted infrastructure, promising lower-latency access to the model.
More from Infra
- Running Qwen Flash Next on a Mac Mini M5 64GB: SSD expert streaming benchmarked with charts — turtleninja99 · 2026-10-18
- Xolotl runs 552B DeepSeek-V4.1-Flash on a single RTX 4090 at ~27 tok/s — indrasmirror · 2026-10-18
- Older Strata silently decodes greedy; ROUTE_TAIL_SKIP=7 halves 4-bit quant quality — Distinct-Pie2389 · 2026-10-18
- Running agent swarms under 6GB VRAM: millisecond micro-models as workers, LLM only for decisions — everettplays · 2026-10-18
- Rust-based Git server on S3 handles 7,600+ concurrent pushes per second — blaizedsouza · 2026-10-18
- Chaining 2 PCs, a MacBook and 2 iPhones Runs 48-Expert MoE at 37 tok/s on 60k Context — StayLameBro · 2026-10-18