Open-Source AI Model Evolution Accelerates
The series tracks the rapid open-source development of large language models and related tooling, from architecture repositories to calibrated decision libraries and fast on-device agents. The latest release of LFM2.5-24B-A2B marks the current focus on high-performance, on-device AI agents.
-
LFM2.5-24B-A2B: Built for fast on-device agents
It is designed for fast, private agents that run entirely on device, with a reasoning‑only architecture that outputs a chain of thought before the final answer. It scored 48.09 on LiveClaw versus…
1 source HN 49 -
Liquid AI Releases Open-Weight LFM2.5-24B-A2B for On-Device Agents
The model is designed for on-device agents and marks the largest release in Liquid AI’s LFM2.5 series, spanning from LFM2.5-230M to this new version. It features a 131,072-token context window,…
1 source -
Aleph Alpha releases Kolibri-1: 78B MoE model with 3.46B active parameters for German and English
{'Kolibri-1 is Aleph Alpha’s open-weight mixture-of-experts model with 78.1 billion parameters, designed for German and English. It activates only 3.46 billion parameters per token, enabling…
5 sources primary source HN 122 -
Contrastive-LM releases CLM-8B, an open model that scores actions up to 9× faster than Jev
Contrastive-LM has released CLM-8B, the first open Contrastive Language Model, which scores candidate actions instead of generating text. The model uses a frozen Qwen3-8B backbone with trainable…
2 sources -
Nokia open-sources AnyJev library to turn open LLMs into calibrated decision models
Nokia’s applied research team released AnyJev, an open‑source Python library that converts any open‑source large language model into a typed decision model without any training. The library reads…
1 source