cs.CLNov 15, 2026

The Vocabulary Tax: Safely Trimming Unused Tokens from LLMs for On-Device Use

Authors: Sattaya Singkul

Organizations: Independent Researcher, Bangkok, Thailand

Abstract

Open large language models (LLMs) and speech models ship vocabularies of up to 262k tokens, and every user downloads the tables those tokens index (the input embedding, an untied output head and, in recent on-device models, per-layer embeddings), whatever languages they need. We call the bytes in rows a deployment never uses the vocabulary tax and measure it, without downloading weights, for 1,244 generative and speech-recognition models on the Hugging Face Hub. For a Thai and English deployment it is a median 4.4% of model bytes below 0.5B parameters and 2.1% above 8B, and 1.93 GB in Gemma 4 E2B: it falls hardest on the small models that edge devices run. Keeping only the rows of the deployment's writing systems is exact. Keeping the tokens seen in the user's own text removes much more, a median 29.0% below 0.5B, but the usual way of doing it breaks BPE tokenizers: it drops the intermediate tokens that merges build on, so new text is split differently 1.9 times as often as the standard check reports. We repair this with merge closure, at a cost of 5.9% more rows, and add a trim certificate: a Good-Turing estimate, from the trimming text alone, of how much new text the trimmed tokenizer will split differently (correlation 0.996 over 300 settings in 22 languages) and of how much more text a target needs. Without test data our method never exceeds a 2% target, while prior keep rules checked on test data exceed it in 9-13 of 44 settings. On six models of 270M to 3B parameters in 11 languages, trimmed models keep their predictions: where the certificate passes, a median 89.7% of rows is removed and bits per character rise by at most 2.0%. The census, the trimming and the certificate are released as an open Python package, and the per-model tax for 41 languages as an open dataset.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jun 18, 2025

Less Is More: Reducing Token Counts Without Compromising Performance

Tokenization directly affects the inference efficiency of large language models, since fragmented tokenization increases sequence length and generation cost. Although longer, multi-word tokens can reduce fertility, naively adding them often degrades language model performance. We propose Thunder-Tok, a subword tokenizer that reduces fertility while preserving downstream performance. Thunder-Tok first constructs a large seed vocabulary from corpus substrings and filters structurally incomplete candidates, including invalid Unicode byte fragments and word-boundary violations. It then prunes the seed vocabulary using a likelihood-based token score derived from a uniform Jensen lower bound of the training-data probability. Experiments show that Thunder-Tok reduces fertility by approximately 25% in English and 9% in Korean compared with the standard BPE tokenizer while maintaining competitive performance.
Aug 28, 2026

Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Registered Negative Result

A byte-level BPE tokenizer is an ordered list of merge rules, so applying only a prefix yields a vocabulary whose token identifiers are the first rows of the full vocabulary. This prefix nesting allows one language model to operate at several vocabulary sizes, use a control token to indicate the active size, and be deployed at any trained size by slicing its embedding and output head. We pre-registered five claims, including margins, seeds, contrasts, and a stop rule, and trained 30 models with 3.1M- and 10.6M-parameter bodies on 200M tokens each. Slicing is numerically exact: across 76 checks, a sliced model reproduces the restricted full model's logits bit for bit and removes 66% of deployed weights without changing latency. However, the shared model trails a fixed-cap specialist by 3.64% bits per byte at 32k against a 1% margin, and by 2.96% at 8k against a 2% margin. A 2x2 ablation separating the control token from output restriction finds that the token changes performance by +0.07% to +0.13%, with all intervals crossing zero, while output restriction costs +0.47% to +1.19%; the factors are substitutes rather than complements. Multi-cap training nevertheless improves robustness: under typographical noise, the same checkpoint degrades 12.5--15.4 points less in its fine mode and outperforms each fixed-cap specialist at that specialist's vocabulary size. A control with neither cap token nor output restriction is equally robust, attributing this benefit to multi-granularity training rather than conditioning. The per-cap penalty tracks each cap's share of training rows, yielding a falsifiable prediction for future work.
Dec 14, 2024

Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning

Tokenization is a necessary component within the current architecture of many language mod-els, including the transformer-based large language models (LLMs) of Generative AI, yet its impact on the model's cognition is often overlooked. We argue that LLMs demonstrate that the Distributional Hypothesis (DH) is sufficient for reasonably human-like language performance (particularly with respect to inferential lexical competence), and that the emergence of human-meaningful linguistic units among tokens and current structural constraints motivate changes to existing, linguistically-agnostic tokenization techniques, particularly with respect to their roles as (1) vehicles for conveying salient distributional patterns from human language to the model and as (2) semantic primitives. We explore tokenizations from a BPE tokenizer; extant model vocabularies obtained from Hugging Face and tiktoken; and the information in exemplar token vectors as they move through the layers of a RoBERTa (large) model. Besides creating suboptimal semantic building blocks and obscuring the model's access to the necessary distributional patterns, we describe how tokens and pretraining can act as a backdoor for bias and other unwanted content, which current alignment practices may not remediate. Additionally, we relay evidence that the tokenization algorithm's objective function impacts the LLM's cognition, despite being arguably meaningfully insulated from the main system intelligence. Finally, we discuss implications for architectural choices, meaning construction, the primacy of language for thought, and LLM cognition. [First uploaded to arXiv in December, 2024.]