Jev may have an open local alternative: Laya.
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Jev may have an open local alternative: Laya. Laya is a 421M-parameter open model for structured decisions, running in <1 GB of memory on laptops and even phones. In a 30-second Snake test: Laya: 46 score, 52 length, 86.5 decisions/s, ~9 ms P50 Jev: 1 score, 7 length, 3.2 decisions/s, 317 ms API cycle On M5 Pro: 15.3 ms local vs 298.1 ms cloud — nearly 20× apart in this test. Laya’s tradeoffs: 512–1024-token context and weaker generalization without additional tuning. Would you run decision-making locally if the task fits?
Posted by David Arnal (1.5k followers) 1 h ago · 0 likes · 35 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- A 27B model just beats GPT-6 Astra & Fable 5.1 by fifty points on CommunicationBench. — @0x0SojalSec
- Respectable for a country that can't legally buy compute and had most of its AI… — @teortaxesTex
- K2-Horizon-36B-A4B scores 25 on the Artificial Analysis Intelligence Index, matching… — @IFM_AI
- Jev-style logit read on a 4B open VLM, measured: http://glance.yohei.me 👀 — @yoheinakajima
- Deepseek Harness w/ GLM 5.3 FLASH Now Has Qwen 2.1 Image Generation Plugin... We… — @Tech2Wild
- Device intelligence is about what an agent delivers within a time and memory budget.… — @liquidai
- Kev looks really cool, with a HF demo you can try right now: — @victormustar
- Introducing the Pirate Face tracker - its distributed hash table (DHT) and BitTorrent… — @thepirateface
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. 39.6k posts from 5k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 18:11 UTC. Full method.