GM-Sparse-LM: Activation-Sparse FFN Execution for Memory-Bandwidth-Bound CPU Inference

Decoding a dense language model on a commodity PC with single-channel memory isbounded by RAM bandwidth, not compute. On an 8 GB single-channel DDR4-3200 laptop(about 11 GB/s effective decode bandwidth), a dense 4B Q4 model is capped at roughly4 tokens per second. This work measures the constraint on real hardware, studies FFNactivation sparsity on Qwen3-0.6B across all 28 layers, and proposes GM-Sparse-LM:an importance-sorted dual-precision FFN layout with masked cold-block execution anda tiered training pipeline (SiLU-to-ReLU conversion, ProSparse-style regularizedfine-tuning, calibration) projected to reach roughly 2.4x speedup at 90 percentsparsity. Measured contributions include a validated byte-level conversion path forGGUF, converted-model benchmarks (the expert-form model reads 25 percent of FFNbytes and gains 1.21x in the bandwidth-bound regime), a measured training-freequality cliff at roughly 37 percent sparsity that matches the sparsity study'soperating point, an implementation finding that explains why prior activation-sparsity systems all ship custom kernels, and eight quantified negative results.Trained-model quality evaluation is in progress.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24423661
Primary Topic
Advanced Neural Network Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

GM-Sparse-LM: Activation-Sparse FFN Execution for Memory-Bandwidth-Bound CPU Inference

Sahil Arun
Zenodo (CERN European Organization for Nuclear Research)
Advanced Neural Network Applications
preprint

GM-Sparse-LM: Activation-Sparse FFN Execution for Memory-Bandwidth-Bound CPU Inference

Sahil Arun
preprint en

Abstract

Decoding a dense language model on a commodity PC with single-channel memory isbounded by RAM bandwidth, not compute. On an 8 GB single-channel DDR4-3200 laptop(about 11 GB/s effective decode bandwidth), a dense 4B Q4 model is capped at roughly4 tokens per second. This work measures the constraint on real hardware, studies FFNactivation sparsity on Qwen3-0.6B across all 28 layers, and proposes GM-Sparse-LM:an importance-sorted dual-precision FFN layout with masked cold-block execution anda tiered training pipeline (SiLU-to-ReLU conversion, ProSparse-style regularizedfine-tuning, calibration) projected to reach roughly 2.4x speedup at 90 percentsparsity. Measured contributions include a validated byte-level conversion path forGGUF, converted-model benchmarks (the expert-form model reads 25 percent of FFNbytes and gains 1.21x in the bandwidth-bound regime), a measured training-freequality cliff at roughly 37 percent sparsity that matches the sparsity study'soperating point, an implementation finding that explains why prior activation-sparsity systems all ship custom kernels, and eight quantified negative results.Trained-model quality evaluation is in progress.

Zenodo (CERN European Organization for Nuclear Research)
Advanced Neural Network Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
GM-Sparse-LM: Activation-Sparse FFN Execution for Memory-Bandwidth-Bound CPU Inference — Sahil Arun · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS