# Replicate — Fine-tuned models now boot in less than one second

- Company: Replicate (replicate.com)
- Announced: 2023-09-06
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://replicate.com/blog/fine-tune-cold-boots
- Record: https://forck.live/items/2555-fine-tuned-models-now-boot-in-less-than-one-second
- Subject: Platform
- Models affected: meta/llama-2-7b-chat, meta/llama-2-13b-chat, meta/llama-2-70b-chat, meta/llama-2-7b, meta/llama-2-13b, meta/llama-2-70b, stability-ai/sdxl

Replicate announced that fine-tuned models now boot in less than one second, dramatically improving cold boot time for specified models including Llama 2 variants and SDXL.

## Evidence

Verbatim from https://replicate.com/blog/fine-tune-cold-boots:

> They now boot in less than one second.

---

Record: https://forck.live/items/2555-fine-tuned-models-now-boot-in-less-than-one-second
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
