Dev Radar
Support
LiveUpdated 2026-09-19 22:52 UTC

A brand new 29B model that only activates 4B parameters AND fits on 1 x 24GB GPU?

A brand new 29B model that only activates 4B parameters AND fits on 1 x 24GB GPU? 🏆Beats Qwen3.6-35B on shared…

This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.

A brand new 29B model that only activates 4B parameters AND fits on 1 x 24GB GPU? 🏆Beats Qwen3.6-35B on shared benchmarks. A China Telecom released Xing4.0-29B-A4B. Stats ... 🧠 29B total parameters ⚡ Only 4B active/token 💾 ~19 GiB IQ4_NL 📚 256K native context → 512K 🤖 Built for agents + coding + tool use 🚀 MLA + MoE + MTP + mHC 📜 Apache 2.0 And the official benchmarks are interesting: 💻 SWE-bench Verified: 75.0 🛠️ Terminal-Bench 2.1: 57.5 🤖 Claw-Eval: 76.55 A llama.cpp support PR appeared basically alongside the release with 👇 ✅ GGUF conversion ✅ IQ4_NL quantization ✅ CPU backend ✅ GPU b

Posted by David Hendrickson (11.1k followers) 2 days ago · 92 likes · 5.5k views · view the original post on X. Kept by the Dev Radar as AI dev tools.

More dev work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.1k posts from 4.7k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 22:52 UTC. Full method.