RunAnywhere

@RunAnywhereAI

Inference research at the frontier. We make frontier open models faster and cheaper on Wally. Backed by @ycombinator W26

runanywhere.ai

Joined July 2025

6 Following

2,503 Followers

Pinned
RunAnywhere
@RunAnywhereAI
Sep 21
Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepSeek-V4.1 Flash: 615 tok/s 1/7
64
RunAnywhere
@RunAnywhereAI
Nov 4
@AnthropicAI is betting up to 5 GW on @awscloud Trainium. We wanted the latest open models flying on it too but there is ZERO support for those. So we wrote megakernels and open-sourced TrnRT: Our Tranium inference engine Running @Zai_org's 320B GLM-5.3-Flash on one Trainium2 box, producing 3.57 M tokens per minute, measured on real coding agent traffic via @SemiAnalysis_'s AgentX.
Andy Jassy
@ajassy
Oct 19
Trying a new AI chip used to be a lot of work. You often had to rewrite your code, revalidate it, and sink many weeks in, betting this new chip is the right one for your workload. That cost time and money, and wore on the team. Your best people got buried in plumbing instead of
15
RunAnywhere
@RunAnywhereAI
Oct 31
We tried this on a real restaurant site that was failing Lighthouse. Told DeepSeek V4.1 Flash on Wally to fix it and 6 seconds later it was done, we hadn't even read the first error
Suraj Sharma
@suraj_sharma14
Oct 30
Every vibe coder's SEO prompt: "My vibe-coded site doesn't show up on Google. Fix it. - Switch to server-side rendering. - Create an XML sitemap. - Submit it in Search Console. - Let Googlebot in through robots.txt. - Strip out every noindex tag. - Collapse the redirect chains.
2
RunAnywhere
@RunAnywhereAI
Oct 30
Coding agents aren't slow because they're dumb. They're slow because every edit waits on the model. We gave OpenCode a real feature request on TodoMVC. DeepSeek V4.1 Flash on Wally shipped drag-to-reorder in about a minute, first try. Waiting is optional now.
RunAnywhere
@RunAnywhereAI
Oct 28
DeepSeek V4.1 Flash vs real CSSBattle targets. It looks at the picture, writes the HTML and CSS, and the first two matched in under two seconds each. Frontend devs, it's been an honor.
1

RunAnywhere

RunAnywhere’s posts