Skip to content
AI News HubLIVE
Original source2 min read

Democratizing AI with Small Language Models: Structured Benchmarking and Parameter-Efficient Fine-Tuning for Local Deployment

Summary

The paper evaluates nine open-weight models from 135M to 3B parameters on a 1,085-example, 16-topic multiple-choice benchmark and then adapts a subset with 4-bit NF4 quantization and DoRA/LoRA adapters on an NVIDIA L4-class budget. Qwen Coder 3B leads base evaluation at 75.67% strict accuracy and gains 26.85 points on a 108-example held-out split, suggesting sub-3B models can serve as local experts for structured niche workloads.

SourcearXiv AIAuthor: Daniel Cersosimo
Democratizing AI with Small Language Models: Structured Benchmarking and Parameter-Efficient Fine-Tuning for Local Deployment
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 5 May 2026]

Title:Democratizing AI with Small Language Models: Structured Benchmarking and Parameter-Efficient Fine-Tuning for Local Deployment

View a PDF of the paper titled Democratizing AI with Small Language Models: Structured Benchmarking and Parameter-Efficient Fine-Tuning for Local Deployment, by Daniel Cersosimo

View PDF HTML (experimental)

Abstract:AI democratization is not primarily a question of matching frontier-scale generality; it is a question of whether capable models can be selected, audited, and specialized under hardware and governance constraints that ordinary institutions can actually satisfy. This paper studies that problem through a controlled evaluation of nine open-weight language models between 135M and 3B parameters on a 1,085-example, 16-topic multiple-choice benchmark designed for structured local deployment. The benchmark emphasizes symbolic precision, constrained formatting, extraction, and short-horizon semantic decision making under a strict one-letter output protocol. A shared parameter-efficient fine-tuning pipeline then adapts a subset of models using 4-bit NF4 quantization with DoRA/LoRA-style adapters on an NVIDIA L4-class budget. In base evaluation, Qwen Coder 3B leads at 75.67% strict accuracy, followed by Qwen2.5 1.5B at 67.10%, Qwen3.5 2B at 64.98%, and Granite 3.3 2B at 64.61%. On the shared 108-example held-out fine-tuning split, adaptation improves Qwen Coder 3B by +26.85 points, SmolLM2 1.7B by +25.92, Qwen2.5 1.5B by +19.44, SmolLM2 360M by +10.18, and SmolLM2 135M by +5.55. Across ranking, topic-level heterogeneity, difficulty strata, failure composition, efficiency frontiers, and topic-conditioned transfer, the same conclusion recurs: a disciplined workflow of benchmark construction, cross-model evaluation, and low-cost specialization already makes a subset of sub-3B models viable as local experts for structured niche workloads.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.16202 [cs.AI]

(or arXiv:2607.16202v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.16202

arXiv-issued DOI via DataCite

Submission history

From: Daniel Cersosimo [view email] [v1] Tue, 5 May 2026 02:36:09 UTC (1,731 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Democratizing AI with Small Language Models: Structured Benchmarking and Parameter-Efficient Fine-Tuning for Local Deployment, by Daniel Cersosimo

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Nine open-weight models between 135M and 3B parameters are tested on a 1,085-example, 16-topic benchmark using a strict one-letter output protocol.
  • Qwen Coder 3B leads base evaluation at 75.67% strict accuracy, followed by Qwen2.5 1.5B, Qwen3.5 2B, and Granite 3.3 2B.
  • On a shared 108-example held-out fine-tuning split, Qwen Coder 3B improves by 26.85 points and SmolLM2 1.7B by 25.92.
  • The author argues AI democratization depends on selecting, auditing, and specializing models under realistic hardware and governance constraints rather than matching frontier generality.

Highlights and analysis are generated automatically and may contain errors. Check the original source.