SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.12844 · 2024

MELTing point: Mobile Evaluation of Language Transformers

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.12844.json · badge: /api/ran/2403.12844.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
brave-experiments/melt-public canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
FunctionStatusWhere it lives
decode_quant_method Ran
ran; our contract draft was wrong, not the code
brave-experiments/melt-public/src/models/convert_utils/awq_utils.py
pointer only (licence: NOASSERTION) · get_code("ebd488c33c6f542b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

llama_change_model_config_eos Ran
ran, honoured the contract we drafted
brave-experiments/melt-public/src/models/convert_utils/llama_utils.py
pointer only (licence: NOASSERTION) · get_code("d4d97ec85344adfa")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

merge_ops Ran
ran, honoured the contract we drafted
brave-experiments/melt-public/src/parsers/utils/utils.py
pointer only (licence: NOASSERTION) · get_code("dc442bca6ccc09ba")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mlc_get_max_length Ran
ran, honoured the contract we drafted
brave-experiments/melt-public/src/models/convert_utils/mlc_utils.py
pointer only (licence: NOASSERTION) · get_code("dcd0cefbbd3a0fb9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mlc_translate_config_to_model_config Ran
ran; our contract draft was wrong, not the code
brave-experiments/melt-public/src/models/convert_utils/mlc_utils.py
pointer only (licence: NOASSERTION) · get_code("e25a568ffee9a3ca")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_json Ran
ran; our contract draft was wrong, not the code
brave-experiments/melt-public/src/parsers/utils/mlc_utils.py
pointer only (licence: NOASSERTION) · get_code("3c0cac5e5b160574")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_logfile Ran
ran; our contract draft was wrong, not the code
brave-experiments/melt-public/src/parsers/utils/mlc_utils.py
pointer only (licence: NOASSERTION) · get_code("08965441176409fe")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_mlc Not yet run
unverified (harvested, no recorded run)
brave-experiments/melt-public/src/models/convert_utils/mlc_utils.py
pointer only (licence: NOASSERTION) · get_code("c682b93b401b16f5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

normalize_calls Not yet run
unverified (harvested, no recorded run)
brave-experiments/melt-public/src/parsers/utils/mlc_utils.py
pointer only (licence: NOASSERTION) · get_code("6834dba45870141d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

parse_file Not yet run
unverified (harvested, no recorded run)
brave-experiments/melt-public/src/parsers/utils/utils.py
pointer only (licence: NOASSERTION) · get_code("ef5a8d3df237c9ff")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

parse_logfile Not yet run
unverified (harvested, no recorded run)
brave-experiments/melt-public/src/parsers/utils/llamacpp_utils.py
pointer only (licence: NOASSERTION) · get_code("9d2469a55dd01a13")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, brave-experiments/melt-public (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Transformers have revolutionized the machine learning landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being broadly deployed on mobile. As personal devices become increasingly powerful and prompt privacy becomes an ever more pressing issue, we explore the current state of mobile execution of Large Language Models (LLMs). To achieve this, we have created our own automation infrastructure, MELT, which supports the headless execution and benchmarking of LLMs on device, supporting different models, devices and frameworks, including Android, iOS and Nvidia Jetson devices. We evaluate popular instruction fine-tuned LLMs and leverage different frameworks to measure their end-to-end and granular performance, tracing their memory and energy requirements along the way. Our analysis is the first systematic study of on-device LLM execution, quantifying performance, energy efficiency and accuracy across various state-of-the-art models and showcases the state of on-device intelligence in the era of hyperscale models. Results highlight the performance heterogeneity across targets and corroborates that LLM inference is largely memory-bound. Quantization drastically reduces memory requirements and renders execution viable, but at a non-negligible accuracy cost. Drawing from its energy footprint and thermal behavior, the continuous execution of LLMs remains elusive, as both factors negatively affect user experience. Last, our experience shows that the ecosystem is still in its infancy, and algorithmic as well as hardware breakthroughs can significantly shift the execution cost. We expect NPU acceleration, and framework-hardware co-design to be the biggest bet towards efficient standalone execution, with the alternative of offloading tailored towards edge deployments.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.12844")
get_code_for_paper("2403.12844")
have("2403.12844")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.12844.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.12844.svg)](https://syntology.ai/paper/2403.12844)

Connect an agent — have() is free.