Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Memory Decoder at Scale: 6.9B Parametric Memory Boosts Small Models Past 12B Baselines

AI By Crimson AI Hugging Face Papers 31 July 2026 · 00:00 21 views
Share: X Telegram

Researchers scale parametric long-term memory to 6.9B parameters and 300B tokens, showing that pairing a small backbone with a large memory outperforms much larger models with fewer total parameters.

Memory Decoder at Scale: 6.9B Parametric Memory Boosts Small Models Past 12B Baselines

Key points

Decoder-only language models typically entangle long-term memory and reasoning within a single parameter set, making it difficult to scale memory capacity independently. A new paper, Memory Decoder at Scale, tackles this by introducing a parametric long-term memory module that can be scaled separately from the base model.

The researchers scale their memory models up to 6.9B parameters and pretrain them on 300B tokens. At this data scale, the combined cost of indexing and search makes a standard Faiss pipeline infeasible. To address this bottleneck, they develop a distributed pipeline for Faiss indexing and retrieval, along with sparse, batch-wise loading of kNN distributions.

Across model scales, the team finds that allocating more parameters to memory yields a better parameter-performance tradeoff than scaling the base model alone. For instance, pairing a 6.9B general memory with Pythia-410M raises its average score from 29.86 to 37.34 on 17 benchmarks, surpassing Pythia-12B (37.24) with 39% fewer total parameters.

For Qwen3 Base models ranging from 0.6B to 14B, adding 1.7B domain memories improves the average score across three domains by more than 9 points at every scale. The results demonstrate that independently scaling pretrained memory offers a more parameter-efficient path to improving language model performance, supporting a "small backbone, large memory" paradigm.

ConfigurationAverage Score (17 benchmarks)Total Parameters
Pythia-410M29.86410M
Pythia-410M + Mem-6.9B37.34~7.3B
Pythia-12B37.2412B
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1