AI Radar
Support
LiveUpdated 2026-09-19 16:24 UTC

k2-horizon-7b-uno

k2-horizon-7b-uno — Uno, the speed-up diffusion-augmented version

k2-horizon-7b-uno is Uno, the speed-up diffusion-augmented version. It is ranked #44 on the AI Radar, in Open & local models, first seen 2 days ago and shared in 5 posts (242.3k views).

Visit huggingface.co

What k2-horizon-7b-uno says about itself

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

What people said about k2-horizon-7b-uno on X

Today’s LLMs still write like typewriters: one token at a time. This sequential process creates a hard inference bottleneck. We're introducing Uno, a diffusion-augmented LLM that delivers autoregressive quality at diffusion speed. It’s a lossless speedup method that accelerates generation without degrading response…

@IFM_AI, 2 days ago · 1k likes · see the post

K2-Horizon-7B scores 21 on Artificial Analysis Intelligence Index, punching above its weights. It scores 50% above the next best model under 10B, beating Qwen3.6-35B-A3B and closely matching Qwen3.6-27B. • Try it: https://huggingface.co/IFM/K2-Horizon-7B • 8-bit quantization:…

@IFM_AI, 2 days ago · 273 likes · see the post

Diffusion can multiply LLM, not just add to it to work in parallel, the outcome is a lossless acceleration of any existing LLMs. Try it out!

@ericxing, 1 days ago · 20 likes · see the post

Alternatives to k2-horizon-7b-uno

k2-horizon-7b-uno in numbers

FAQ

What is k2-horizon-7b-uno?

Uno, the speed-up diffusion-augmented version It was first shared on X 2 days ago and is ranked #44 on the AI Radar.

Is k2-horizon-7b-uno free?

It is open source.

Who shared k2-horizon-7b-uno?

4 accounts on X, including @IFM_AI, @ericxing, @mr_r0b0t, in 5 posts totalling 242.3k views.

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. 27k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 16:24 UTC. Full method.