Cover Image

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Yixin, Xue, Zhenliang, Wei, Dongliang, Chen, Feiyang, Gao, Jianxiang, Liu, Junchen, Liang, Hangyu, Qin, Guangshuo, Tian, Chengrong, Wen, Bo, Zhao, Longyu, Zheng, Xinrui, Mi, Zeyu, Chen, Haibo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PowerInfer-2: Fast Large Language Model Inference on a Smartphone
by: Xue, Zhenliang, et al.
Published: (2024)

DIP: Efficient Large Multimodal Model Training with Dynamic Interleaved Pipeline
by: Xue, Zhenliang, et al.
Published: (2025)

PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
by: Song, Yixin, et al.
Published: (2023)

PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption
by: Tan, Yifan, et al.
Published: (2024)

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
by: Wen, Hao, et al.
Published: (2025)

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters
by: Song, Yixin, et al.
Published: (2024)

Local-in-time well-posedness for 2D compressible magneto-micropolar boundary layer in Sobolev spaces
by: Qin, Yuming, et al.
Published: (2025)

ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
by: Wen, Hao, et al.
Published: (2025)

FASTNav: Fine-tuned Adaptive Small-language-models Trained for Multi-point Robot Navigation
by: Chen, Yuxuan, et al.
Published: (2024)

Compass-Thinker-7B Technical Report
by: Zeng, Anxiang, et al.
Published: (2025)

The Thinker
Published: (2021)

Characterizing Model-Native Skills
by: Kang, Feiyang, et al.
Published: (2026)

Towards Family-Grouped Hierarchical Federated Learning on Sub-5KB Models: A Feasibility Study of Privacy-Preserving ECG Monitoring for Ultra-Resource-Constrained Wearables
by: Wu, Hangyu
Published: (2026)

Local/Short-range conformal field theories from long-range perturbation theory
by: Rong, Junchen
Published: (2024)

HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
by: Yan, Xin, et al.
Published: (2026)

VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models
by: Qin, Guangshuo, et al.
Published: (2026)

ProxyThinker: Test-Time Guidance through Small Visual Reasoners
by: Xiao, Zilin, et al.
Published: (2025)

Intergenerational coparenting relationship patterns and grandparents' psychological well‐being: Evidence from the China Family Panel Studies
by: Meihua Wang, et al.
Published: (2025)

Long time well-posedness for the 3D Prandtl boundary layer equations with a special structure
by: Qin, Yuming, et al.
Published: (2024)

japan_mpa
by: Li, Longyu
Published: (2025)

Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
by: Xu, Jun, et al.
Published: (2025)

TPLogAD: Unsupervised Log Anomaly Detection Based on Event Templates and Key Parameters
by: Lu, Jiawei, et al.
Published: (2024)

Favorite sites of one-dimensional asymmetric simple random walk
by: Zhou, Guangshuo, et al.
Published: (2025)

A machine learning based prediction model for the impact mechanical response of composite laminates considering microstructure sensitive transverse properties
by: Zhang Yiben, et al.
Published: (2024)

A Comprehensive Evaluation Framework for Synthetic Trip Data Generation in Public Transport
by: Wu, Yuanyuan, et al.
Published: (2025)

The Thinker by Auguste Rodin
by: rigsters
Published: (2021)

Quantitative Parameter Conditions for Stability and Coupling in GFM-GFL Converter Hybrid Systems from a Small-Signal Synchronous Perspective
by: Zhuang, Kehao, et al.
Published: (2025)

Exploring Human-Machine Coexistence in Symmetrical Reality
by: Zhang, Zhenliang
Published: (2026)

V-Thinker: Interactive Thinking with Images
by: Qiao, Runqi, et al.
Published: (2025)

LightThinker: Thinking Step-by-Step Compression
by: Zhang, Jintian, et al.
Published: (2025)

Global Pre-fixing, Local Adjusting: A Simple yet Effective Contrastive Strategy for Continual Learning
by: Tang, Jia, et al.
Published: (2025)

RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models
by: Zheng, Zihao, et al.
Published: (2026)

On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices
by: Huang, Lianming, et al.
Published: (2025)

LaSe-E2V: Towards Language-guided Semantic-Aware Event-to-Video Reconstruction
by: Chen, Kanghao, et al.
Published: (2024)

HeteroPod: XPU-Accelerated Infrastructure Offloading for Commodity Cloud-Native Applications
by: Yang, Bicheng, et al.
Published: (2025)

LSAI: A Large Small AI Model Codesign Framework for Agentic Robot Scenarios
by: Zhou, Longyu, et al.
Published: (2026)

Variety Evasive Subspace Families
by: Guo, Zeyu
Published: (2021)

TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba
by: Ma, Xiaowen, et al.
Published: (2024)

SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation
by: Ma, Xiaowen, et al.
Published: (2024)

VeriThinker: Learning to Verify Makes Reasoning Model Efficient
by: Chen, Zigeng, et al.
Published: (2025)