Tiiny AI

community

https://tiiny.ai/

AI & ML interests

We are committed to advancing the field of AGI by pushing the boundaries of local LLM inference efficiency.

submitted a paper to Daily Papers 3 months ago

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

Paper • 2605.10933 • Published May 11 • 4

updated 2 models 12 months ago

Tiiny/SmallThinker-21BA3B-Instruct-GGUF

Text Generation • 22B • Updated Aug 5, 2025 • 905 • 38

Tiiny/SmallThinker-4BA0.6B-Instruct-GGUF

Text Generation • 4B • Updated Aug 5, 2025 • 526 • 36

in Tiiny/SmallThinker-21BA3B-Instruct-GGUF 12 months ago

SmallThinker-21B-A3B-Instruct-QAT training details?

#3 opened 12 months ago by

in Tiiny/SmallThinker-21BA3B-Instruct about 1 year ago

Are there any other frameworks tested besides transformers that can be deployed?

#5 opened about 1 year ago by

Improve model card: Add paper title and abstract

#4 opened about 1 year ago by

in Tiiny/SmallThinker-4BA0.6B-Instruct about 1 year ago

Enhance model card: Add abstract and project page

#4 opened about 1 year ago by

in Tiiny/SmallThinker-21BA3B-Instruct about 1 year ago

怎样在rk3588运行

#3 opened about 1 year ago by

authored 2 papers about 1 year ago

PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption

Paper • 2411.03357 • Published Nov 4, 2024

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

Paper • 2507.20984 • Published Jul 28, 2025 • 59

in Tiiny/SmallThinker-21BA3B-Instruct about 1 year ago

Improve model card: Add library, paper, GitHub links, and MoE tag

#2 opened about 1 year ago by

in Tiiny/SmallThinker-4BA0.6B-Instruct about 1 year ago

Improve model card: Add `library_name`, explicit paper and code links

#3 opened about 1 year ago by

smallscientist1

authored a paper about 1 year ago

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

Paper • 2507.20984 • Published Jul 28, 2025 • 59

updated a model about 1 year ago

Tiiny/SmallThinker-4BA0.6B-Instruct-INT4-QAT

4B • Updated Jul 29, 2025 • 105 • 1

authored a paper about 1 year ago

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

Paper • 2507.20984 • Published Jul 28, 2025 • 59

authored a paper about 1 year ago

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

Paper • 2507.20984 • Published Jul 28, 2025 • 59

published a model about 1 year ago

Tiiny/SmallThinker-4BA0.6B-Instruct-INT4-QAT

4B • Updated Jul 29, 2025 • 105 • 1

BLGS

updated 2 models about 1 year ago

Tiiny/SmallThinker-21BA3B-Instruct-GGUF

Text Generation • 22B • Updated Aug 5, 2025 • 905 • 38

Tiiny/SmallThinker-4BA0.6B-Instruct-GGUF

Text Generation • 4B • Updated Aug 5, 2025 • 526 • 36

in Tiiny/SmallThinker-4BA0.6B-Instruct-GGUF about 1 year ago

无法复现smallthinker-4ba0.6b在8elite手机上的性能数据

#1 opened about 1 year ago by