tensorfold
tensorfold is Patch and receipts. It is ranked #418 on the AI Radar, in Open & local models, first seen 41 days ago and shared in 36 posts (306.7k views).
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
I'm launching TensorFold StarLight to help fund the next stage of TensorFold's journey. 🌟 Subscribers, donors, contributors and everyone who's lent me hardware have helped get TensorFold this far, I'm incredibly grateful for that support. You are amazing!!! 🫶🏼 There is still a lot more development to do and…
— @ashxhart, 3 days ago · 45 likes · see the post
TensorFold now runs on Apple M1 GPUs under Linux via a native Vulkan backend. 🤯 👇🏼
— @ashxhart, 9 days ago · 42 likes · see the post
My TensorFold patch makes Qwen3.8-27B process prompts about 10% faster on an M5 Ultra, with identical tokens. Mac Studio M5 Ultra (256 GB), TensorFold before my patch: Prefill, 2K prompt: 1,722 tok/s Prefill, 8K prompt: 1,679 tok/s Prefill, 32K prompt: 1,517 tok/s Prefill, 64K prompt: 1,173 tok/s Mac Studio M5 Ultra…
— @niklaslenz_ai, 5 days ago · 38 likes · see the post
Alternatives to tensorfold
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- project-maya — Plus a round of fixes, UI improvements and community PRs.
- twil-8b — Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
tensorfold in numbers
- Rank on the AI Radar: #418 of 10402
- Shared in 36 posts by 14 accounts: @ashxhart, @niklaslenz_ai, @TheDavidTai, @volatilemarkts
- 306.7k views on those posts
- First seen 41 days ago, last shared 3 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Open & local models
FAQ
What is tensorfold?
Patch and receipts It was first shared on X 41 days ago and is ranked #418 on the AI Radar.
Is tensorfold free?
It is open source.
Who shared tensorfold?
14 accounts on X, including @ashxhart, @niklaslenz_ai, @TheDavidTai, in 36 posts totalling 306.7k 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. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.