← Back to all news
arXiv Machine Learning By Luka Ribar, Jeevan Bhoot, Douglas Orr

Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs

Read the original on arXiv Machine Learning →

The paper introduces Llama-Mobile, a framework that quantizes vision‑language models for efficient mobile deployment. It uses a quantization pipeline that generates training data from the model itself, eliminating the need for the original training setup, and employs a novel 2.7‑bit‑per‑parameter format optimized for Arm CPUs. Applying this method, the authors compress the Llama 3.2 11B Vision Instruct model to 3.7 GB with 8‑bit activations while maintaining strong performance on visual question answering tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 4

Efficient Reasoning on the Edge

arXiv:2603. 16867v2 Announce Type: replace Abstract: Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge deployment.

By Yelysei Bondarenko, Thomas Hehn, Rob Hesselink, Romain Lepert, Fabio Valerio Massoli, Evgeny Mironov, Leyla Mirvakhabova, Tribhuvanesh Orekondy, Spyridon Stasis, Andrey Kuzmin, Anna Kuzina, Markus Nagel, Ankita Nayak, Corrado Rainone, Ork de Rooij, Paul N Whatmough, Arash Behboodi, Babak Ehteshami Bejnordi
llmsreinforcement-learningfine-tuningefficiencybenchmarks
More like this →
arXiv AI
Aug 28

PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference

PACE introduces a training‑free Condense‑and‑Extract framework that speeds up Vision‑Language Model inference by first adaptively downsampling visual inputs before encoding and then selectively retaining essential tokens during decoding. The Adaptive Pixel Compressor (APC) reduces encoder workload while preserving global context, and the Dynamic Dual‑Attention Extractor (DDAE) keeps task‑critical details by fusing visual and language signals. Applied to Qwen2.5‑VL‑7B, PACE maintains 93.8% of performance using only 10% of visual tokens, achieving a 3.1× speedup in time to first token.

By Junjie Liu, Shengyuan Ye, Xu Chen
llmsefficiencymultimodal
More like this →