Benchmarked Jev with Qwen3-4B and Laya (400M parameter model).
This is a AI post classified by Jev as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.
Benchmarked Jev with Qwen3-4B and Laya (400M parameter model). Based on results here and others I've seen online, strongly suspect Jev to be in 30Bn range (compare 4bn results on MMLU vs Jev). Latency I got was 300ms, same as you'd get for a 30bn model on a good GPU. Also interesting that on relational choice benchmark where one choice impacts another, Jev scores 0%, suggesting that not only questions are processed in parallel, perhaps options are processed in parallel too. So Jev seems like mostly a standard modern model with specific fast-inference related tradeoffs.
Posted by Paras Chopra (238.7k followers) 5 h ago · 104 likes · 7.1k views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- Here's a useful use-case for @typesafeai for a change. — @iam_zachi
- This is genius. — @daniel_mac8
- Which GPU should you use for embedding workloads? — @runpod
- Big update to the @Alibaba_Qwen Qwen3.8-Flash-Next single DGX Spark recipe! — @jvr0x
- 🔰 The Databricks Advanced Learning Festival runs September 16 through October 14, with… — @databricks
- Q: What is a trace? — @HamelHusain
- Inference scaling part 1. — @rasbt
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. 27.2k 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 18:08 UTC. Full method.