Strata 0.2.9 speeds up local model prefill by 88%
10/31/2026 — 10/31, 18:17·1 sources (all)·1 reports (all)
Key takeaways
- Strata, a local large-model runner, has shipped version 0.2.9, which cuts prefill time for local models by up to 88%, according to Xiaozhong…
Background & analysis
On October 31, 2026, a report on the Chinese software site Xiaozhong Ruanjian (小众软件) covered the release of Strata 0.2.9, a tool for running large language models locally. According to the report, the update raises Prefill throughput for local LLMs by up to 88 percent, adds support for 1-bit DeepSeek, and concentrates its improvements on the Windows platform. The site describes Strata as a program updated on a near-daily basis, and frames this release as a further step in its ongoing effort to speed up local model inference. The figures cited, including the 88 percent Prefill improvement and the 1-bit DeepSeek support, come solely from this report, and no independent verification or subsequent updates were available at the time of writing. No other details about pricing, documentation, or planned follow-up features were mentioned in the coverage.
AI-generated from 1 reports · updated 5 days ago
- Heat index
- 25
- All sources
- 1
- All reports
- 1
- First seen
- 5 days ago
Reports on this story headlines open the original
Strata, a tool for running large language models locally, has been updated to version 0.2.9. According to Xiaozhong Software, the release speeds up prefill by up to 88% and adds support for 1-bit DeepSeek, with the changes focused on Windows.
小众软件AI score 53
Other stories people are talking about
- Heat index 840OpenAI ships Images 2.6 with GIF and SVG output15 sources
- Heat index 675OpenAI says its cyber model pipeline confirmed 1,724 Linux kernel flaws and generated 948 privilege-escalation exploits11 sources
- Heat index 642RisingOpenAI GPT-5.6 Brings Major Agentic and Computer Use Upgrades13 sources
- Heat index 633RisingCat Wu, product lead for Claude Code, joins OpenAI9 sources
- Heat index 630NewSurgeOpenAI releases GPT-6 Cyber cybersecurity model7 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

