Dev Radar
Support
LiveUpdated 2026-10-30 20:22 UTC

tensorfold

tensorfold — I’d love community feedback to make it better

tensorfold is I’d love community feedback to make it better. It is ranked #106 on the Dev Radar, in AI dev tools, first seen 34 days ago and shared in 43 posts (417.4k views).

Visit github.com

What tensorfold says about itself

Rebased onto 0.3.4.1 (bb4b4a3) and grown a little since the last push: GLM-5.3-Flash rides the lane engine's family rounds on a Mac, prefills on the 2,048-token grid like every other family, re...

feat: GLM-5.3-Flash on Apple Silicon (glm5_next MLX family) — rebased on 0.3.4 by chadhurley25075-png · Pull Request #9 · ashhart/TensorFold · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation feat: GLM-5.3-Flash on Apple Silicon (glm5_next MLX family) — rebased on 0.3.4 - # 9 # 9 Closed chadhurley25075-png…

What people said about tensorfold on X

TensorFold 1.0.7 has landed with a major overhaul to Living Weights. • Each fact you teach through /learn becomes about ten new neurons inside the model's own weights, learned about 4x faster, with a live 3D view of what it has learned. Macs and DGX Spark. • Structured output and required tool calls on the native…

— @ashxhart, 19 days ago · 277 likes · see the post

TensorFold 1.0.5 is out: - GLM-5.3-Flash runs on one 256 GB M5 Ultra - Nemotron reuses your chat: a 19.8k-token chat's next turn prefills in 0.16 s, not 8.1 s - Fixed: the 27B on macOS 27, and a request that could crash the server I’m re working the Living Weights which will be in the next release. Thank you to…

— @ashxhart, 20 days ago · 315 likes · see the post

Tonight we brought @ashxhart's Living Weights to GLM-5.3. Living Weights lets a running model learn facts straight into its own weights. Ash shipped it in TensorFold 1.0.3 for Nemotron. We ported it to GLM.. (Lets be honest, we are "me and my coding agent") Full GLM-5.3 (753B), split across four M3 Ultra Mac Studios,…

— @volatilemarkts, 20 days ago · 260 likes · see the post

Alternatives to tensorfold

tensorfold in numbers

FAQ

What is tensorfold?

I’d love community feedback to make it better It was first shared on X 34 days ago and is ranked #106 on the Dev Radar.

Is tensorfold free?

It is open source.

Who shared tensorfold?

10 accounts on X, including @ashxhart, @volatilemarkts, @MiaAI_lab, in 43 posts totalling 417.4k views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:22 UTC. Full method.