Paper Citation Record · LEDGER

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs

As of 14 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2608.04488.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.04488 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:25:10.361903Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

46 of 46 outbound references displayed

verified exact5
verified fuzzy5
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3fd1d063-c31e-4dc6-951f-8e1a0fd2e0d4 · outbound

This paper cites Attention Is All You Need.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Attention Is All You Need

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:08.162717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5333ec8e-da53-4bde-9d28-b8244f833407 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:08.229945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73f10c43-5021-45df-a5c6-0e61e2a89114 · outbound

This paper cites Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:08.295434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b4cdb1a-4174-44a9-877b-bed67f69f5cf · outbound

This paper cites Training Compute-Optimal Large Language Models.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Training Compute-Optimal Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:08.418115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 017bb74a-979e-4352-8809-c3a8a129d0a2 · outbound

This paper cites A cost-benefit analysis of on-premise large language model deployment: Breaking even with commercial llm services,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs A cost-benefit analysis of on-premise large language model deployment: Breaking even with commercial llm services,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:08.487893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb685d05-ec36-49ab-960d-01c7061947ec · outbound

This paper cites Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-06T23:25:10.883750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 99770478-6db3-483e-b240-f34bf9c1266c · outbound

This paper cites Understanding the Performance and Estimating the Cost of LLM Fine-Tuning.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Understanding the Performance and Estimating the Cost of LLM Fine-Tuning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:08.608483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e679d980-e22e-4046-9d29-9b755292079c · outbound

This paper cites Small Language Models are the Future of Agentic AI.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Small Language Models are the Future of Agentic AI

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:08.702584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80ac4c7d-f9fc-4652-b354-65b15ae69667 · outbound

This paper cites A survey on small language models,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs A survey on small language models,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:25:11.059154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9e53ab91-50d8-47b5-9856-d9d236b72474 · outbound

This paper cites It’s not just size that matters: Small language models are also few-shot learners,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs It’s not just size that matters: Small language models are also few-shot learners,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:25:11.049868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1c09d827-bf61-4389-8d18-4dd95f5aaee3 · outbound

This paper cites Small Language Models: Survey, Measurements, and Insights.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Small Language Models: Survey, Measurements, and Insights

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:08.951439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00d746b7-272a-4bc4-8426-66d5484bd501 · outbound

This paper cites Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026).

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:09.044619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75aefdf6-d6b6-47b4-a2a1-844689fc5e33 · outbound

This paper cites Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:09.117752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f245ee31-4d82-442b-a91c-1320a36bed56 · outbound

This paper cites PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:09.204667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6b58bc9-48f4-48ea-8bd6-49bd1db75cca · outbound

This paper cites Parameter efficient fine tuning: A comprehensive analysis across applications,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Parameter efficient fine tuning: A comprehensive analysis across applications,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:25:11.040366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fe3a21cf-1a1e-41c2-8f91-06e1b6e4b13d · outbound

This paper cites Parameter-Efficient Fine-Tuning for Foundation Models.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Parameter-Efficient Fine-Tuning for Foundation Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:09.452833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b5e4a6c-55b0-48b6-af5d-2fbdefca121a · outbound

This paper cites NetScore: Towards Universal Metrics for Large-scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usage.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs NetScore: Towards Universal Metrics for Large-scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usage

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:09.580362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bea53fa0-7308-406b-9670-e212d8c5e71c · outbound

This paper cites AttoNets: Compact and Efficient Deep Neural Networks for the Edge via Human-Machine Collaborative Design.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs AttoNets: Compact and Efficient Deep Neural Networks for the Edge via Human-Machine Collaborative Design

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:09.741474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc8777c5-1160-49ab-a97c-3ec2034f605d · outbound

This paper cites How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-06T23:25:10.778139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cacfc435-5a8b-49e8-810d-f3889408fbf0 · outbound

This paper cites An attention-based feature memory design for energy-efficient continual learning,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs An attention-based feature memory design for energy-efficient continual learning,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.033991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 655aa492-db25-4aba-af02-160cae799fb5 · outbound

This paper cites Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-06T23:25:10.676677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ae840744-08d4-4b5d-985d-c520fc8b969d · outbound

This paper cites Lora: Low-rank adaptation of large language models,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Lora: Low-rank adaptation of large language models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.217852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44c39bbb-6b75-448a-bedb-4e324a9e3582 · outbound

This paper cites LoRA+: Efficient Low Rank Adaptation of Large Models.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs LoRA+: Efficient Low Rank Adaptation of Large Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.291996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8417260a-3c1d-4078-9265-c2c2da91fd51 · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs QLoRA: Efficient Finetuning of Quantized LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.295446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1428ed85-1590-47b3-b8e0-54a763ca4c4b · outbound

This paper cites Bitfit: Simple parameter- efficient fine-tuning for transformer-based masked language-models,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Bitfit: Simple parameter- efficient fine-tuning for transformer-based masked language-models,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:25:11.023887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cdb6da5a-a3c2-4b90-9f2b-e93652809269 · outbound

This paper cites A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.306623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28cb4b2-d610-4d4e-a4dd-3d0d16e5125a · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs TinyLlama: An Open-Source Small Language Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.309716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a59ae93-a443-4577-8815-190cfe407a8b · outbound

This paper cites Qwen3 technical report,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Qwen3 technical report,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.313605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df68e60-8d33-47ef-90e0-ca5638b32e6f · outbound

This paper cites MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.320329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b45a68ae-0c7c-41d0-82e5-a88cb3a1253c · outbound

This paper cites Demystifying small language models for edge deployment,.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Demystifying small language models for edge deployment,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:25:11.006416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation faf94f5f-7515-4e9f-b336-a41ab59824ac · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.326843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20c58eb9-7600-4a38-ae2d-ce1625dc3d02 · outbound

This paper cites Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.329751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23114d8d-44aa-4dcf-97a9-3062bd7e2306 · outbound

This paper cites GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.332835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab9a3bbc-3e7c-41c7-9115-830d908cee90 · outbound

This paper cites LaMP: When Large Language Models Meet Personalization.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs LaMP: When Large Language Models Meet Personalization

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.336161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6e87864-6c1c-466a-bb88-1a0d5527a17f · outbound

This paper cites PID Parameters Optimization by Using Genetic Algorithm.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs PID Parameters Optimization by Using Genetic Algorithm

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-06T23:25:10.475733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9fcc7cce-6438-492d-bac7-96833fe452de · outbound

This paper cites SQuAD: 100,000+ Questions for Machine Comprehension of Text.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs SQuAD: 100,000+ Questions for Machine Comprehension of Text

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.342592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96e373bb-070a-4ab7-8d2a-6af312e767f6 · outbound

This paper cites Unsupervised Dense Information Retrieval with Contrastive Learning.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Unsupervised Dense Information Retrieval with Contrastive Learning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.345832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18746a5b-0cc3-4967-8c25-683a0500e774 · outbound

This paper cites Parameter-Efficient Fine-Tuning of State Space Models.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Parameter-Efficient Fine-Tuning of State Space Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.349083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e93dc94-463f-4ef5-93a5-b9c9061b1296 · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.352431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 200549dc-d921-4109-8bf5-e377a06fe0fa · outbound

This paper cites Quamba: A Post-Training Quantization Recipe for Selective State Space Models.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Quamba: A Post-Training Quantization Recipe for Selective State Space Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.355759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf345921-9ff4-4f4e-806d-fc0ef3ddcbd8 · outbound

This paper cites MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.358968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4ed56a8-ea86-4ed8-ab12-4a921f77b6b4 · outbound

This paper cites Mamba State-Space Models Are Lyapunov-Stable Learners.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Mamba State-Space Models Are Lyapunov-Stable Learners

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-08-06T23:25:10.397889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c29453e7-a762-40d3-a575-a0326d844a50 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs LoRA: Low-Rank Adaptation of Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.288646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 784e7f57-e3b0-4728-b339-f3a89d55b769 · outbound

This paper cites Available: https://arxiv.org/abs/2106.10199.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Available: https://arxiv.org/abs/2106.10199

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.302674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2930e22a-e666-403e-b8aa-0f8b745da9b9 · outbound

This paper cites Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:09.288553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8aac230-a5cc-4fcd-852d-fa82d34c04c1 · outbound

This paper cites Qwen3 Technical Report.

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs Qwen3 Technical Report

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:10.317049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.