SOURCE-LINKED INTELLIGENCE

ufakzeka-1: Building and Evaluating a 151M-Parameter Turkish Language Model from Scratch

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

We describe ufakzeka-1, a 151M-parameter (182M with embeddings) decoder-only Turkish language model pretrained from scratch on 13.5B tokens of openly licensed text and instruction-tuned for chat, at a total cost of about \$286 in cloud GPU, API and notebook time. The contribution is not the model's capability, which is what a model this size can be expected to have, but the record of building and measuring it: a Turkish byte-level tokenizer at 1.77 tokens per word, a three-stage pretraining schedule, a post-training mixture of openly licensed and generated data, and an evaluation battery of re

Read original source ↗ Open in workspace

recordType

paper

region

Global