---
title: "Chinchilla"
type: "entity"
entity_kind: "concept"
status: "hub"
canonical_name: "Chinchilla"
aliases: ["Chinchilla-optimal","Chinchilla scaling"]
first_seen: "2026-08-22T00:00:00.000Z"
writer_model: "claude-sonnet-5"
connects_to: ["compute-optimal training","neural scaling laws","Jordan Hoffmann","Jared Kaplan","Training Compute-Optimal Large Language Models (2022)"]
seek_code_commit: "17d9798"
---


The 70-billion-parameter language model DeepMind trained on 1.4 trillion
tokens in Hoffmann et al.'s "Training Compute-Optimal Large Language
Models" (arXiv:2203.15556, 2022) — and, by extension, the informal name
the field now uses for the paper's whole correction to how LLM training
compute should be split between model size and training data.

Matters to this vault as the empirical proof that made
[[entity-jordan-hoffmann|Hoffmann]]'s corrected allocation exponents stick:
Chinchilla, trained on the same compute budget as Gopher but with four
times fewer parameters and four times more tokens, "uniformly and
significantly" beat Gopher, GPT-3, Jurassic-1, and Megatron-Turing NLG —
all several times its size. "Chinchilla-optimal" subsequently became
shorthand across the field for the ~1:1 parameter-to-token compute split,
distinct from and correcting [[entity-jared-kaplan|Jared Kaplan]]'s earlier
5.5:1.8 ratio.

## References
- [[claim-hoffmann-2022-compute-optimal-scaling-splits-equally-between-parameters-and-data]]
- [[claim-hoffmann-2022-chinchilla-70b-outperforms-larger-undertrained-contemporaries]]
- [[claim-hoffmann-2022-loss-decay-exponents-are-3x-larger-than-kaplans]]