sumo43/jetspec_qwen38_nvfp4 — GitHub trending stats & insights | Trendshift

Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

Terms and conditions
Privacy policy

More

Pricing
Advertise
onedump
gosnakego
Contact us

Social

X (Twitter)
GitHub

What they build speaks louder than words

© 2026 Trendshift, created by Julian Li with ❤️

Signal Advertise

Signal Advertise

Discover trends that matter

Daily Weekly Monthly Yearly

Live mentions Topics

Repositories Developers

sumo43/jetspec_qwen38_nvfp4 — GitHub trending stats & insights | Trendshift

sumo43/jetspec_qwen38_nvfp4

Fast inference for a single user on a B200 for Qwen 3.8

Python

0

MIT License

Social mentions

Recent discussions about this repository across the web

I reached 950 decode tok/s on competitive math problems and 715 tok/s for agentic coding tasks using Qwen3.8 27B running on a single B200. To hit these numbers, I use JetSpec/DDTree with DFlash2,…

@artemsya · x.com

Repository activities

repository's daily and monthly activities across stars, forks, merged PRs, issues, and closed issues

Data is not available yet

Recent activity data for stars, forks, merged PRs, issues, and closed issues will appear here once available

Featured

Control what AI can do before it acts

Run LLMs locally in Flutter, React Native, Swift, Kotlin, Python and Godot

Your agents build it. Kane verifies it. Writes the tests, runs them, and maintains them

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

180K+ monthly visitors

Want to advertise your product to high-intent tech audiences at a simple, flat rate?

Advertise on Trendshift