Malandrino PRO

Pier-Jean

·

AI & ML interests

Document parsing Quantization

Recent Activity

updated a Space 2 days ago

Pier-Jean/docling-studio

authored a paper 5 days ago

Tetra: Serving Leech-Lattice Quantized LLMs at 2.7 Bits per Parameter

updated a model 9 days ago

Pier-Jean/Qwen3-4B-LLVQ-Tetra-served

View all activity

Organizations

Articles 3

Article

I put a 24 dimensional lattice in a CUDA kernel to run Qwen3-4B in 2.6 GB

Article

1

Docling Studio — Open-Source Visual Inspection for Docling Pipelines

View all Articles

Papers 2

arxiv:2609.35465

arxiv:2609.02652

spaces 1

Docling Studio

Edit and preview documents instantly online

models 11

Pier-Jean/Qwen3-4B-LLVQ-Tetra-served

Updated 9 days ago

Pier-Jean/Qwen3-4B-LLVQ-Tetra-sealed

Updated 22 days ago

Pier-Jean/Qwen3-4B-LLVQ-Tetra

Text Generation • 1B • Updated 22 days ago • 537

Pier-Jean/tiny-qwen3-llvq

65.1k • Updated Oct 7 • 4

Pier-Jean/Qwen3-14B-LLVQ-Tetra-sealed

Pier-Jean/Qwen3-8B-LLVQ-Tetra-sealed

Pier-Jean/Qwen3-4B-LLVQ-2bit

Pier-Jean/qwen3-8b-awq-deq

8B • Updated Aug 7 • 4

Pier-Jean/qwen3-4b-awq-deq

4B • Updated Aug 6 • 7

Pier-Jean/scubsql-coder

Updated Aug 4, 2024

datasets 0

None public yet