PulseAugur
EN
LIVE 13:25:49

Janas Engine Enables Large AI Models on Laptops by Streaming from SSD

By PulseAugur Editorial · [1 sources] ·

A new language model engine called Janas, written in C by Maurizio Cammalleri, claims to significantly improve the performance of large AI models on consumer hardware. Janas reportedly achieves 37 tokens per second for a 48 GB model on a laptop with 32 GB of RAM, a substantial improvement over existing methods like llama.cpp. The engine achieves this by keeping model weights on disk and selectively caching frequently used "experts," while also utilizing speculative drafting to speed up token generation. AI

IMPACT This engine could enable more users to run large, powerful AI models locally on standard hardware, democratizing access and reducing reliance on cloud infrastructure.

RANK_REASON The item describes a new software engine that improves the performance of existing AI models on consumer hardware, rather than a new model release or fundamental research.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Janas Engine Enables Large AI Models on Laptops by Streaming from SSD

How we ranked this

Signal score
28 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a new software engine that improves the performance of existing AI models on consumer hardware, rather than a new model release or fundamental research.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
infra, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · jamilxt ·

    Run a 48 GB AI Model on a 32 GB Laptop: Janas Streams Model Experts From Your SSD at 37 tok/s

    <p>The wall everyone hits with local models is always the same one: the model you actually want to run is bigger than your memory. You find a promising 80B mixture-of-experts model, check the file size, see 48 GB, look at your 32 GB of RAM, and close the tab. Or worse, you try it…

RELATED ENTITIES

RELATED TOPICS