NaiveAI

Headlines · 2

1. 8h
   Naive-N0.5-Flash open-weights coding model prioritizes speed

   NaiveAI released Naive-N0.5-Flash, an open-weights model for AI coding that continues training from Xiaomi’s MiMo-V2.5 and runs with the NaiveRT inference engine. Latent Space found that it answered faster overall than DeepSeek V4.1 Flash 1017 and GLM 5.3 Flash in limited tests, but it took longer on harder questions and had a slightly higher cost per question. NaiveAI reports about 984 tokens per second during thinking and 1,816 tokens per second while producing the answer, with a roughly 2,100-token-per-second peak measured on a single eight-GPU Blackwell node.

   Latent Space · 🔥 8
2. 4d
   Naive-N0.5-Flash automates parts of model training

   New Zhiyuan reports that the open-source Naive-N0.5-Flash can handle parts of model-training workflows, including data preparation, training, evaluation, and identifying flaws in scoring rules. In a community project described by the outlet, a creator used Naive-N0.5-Flash through Claude Code to fine-tune a 0.6B model on a 24GB Mac after writing a one-page task specification. New Zhiyuan also says it used the system on a 64GB Mac to train a locally running, 110-million-parameter BERT classifier for the BANKING77 dataset. The outlet reports 93.34% accuracy on the official test set and a 6.77-millisecond median response time, while noting that the workflow still requires a human-written program.md and researcher intervention.

   新智元 · 🔥 0

Experience and discussion from the community

Share my NaiveAI experienceAsk about NaiveAI