Ollama - Page 9
Stories from Ollama come first, newest first, then stories from connected topics (MLX, llama.cpp, Local AI, NVIDIA RTX Spark, Machine Learning, AI Models), each labelled with where it comes from. This view is not indexed by search engines.
Latest
AWS Makes Its AI/ML Skill a Core Part of the Agent Toolkit, Taking Coding Agents From Inference Tuning to Full SageMaker Workflows
AWS's AI/ML skill is now a core Agent Toolkit skill, so coding agents can select, train, optimise and deploy SageMaker AI models in plain language.
NVIDIA Says Its DLSS 5 Model Is Now Twice as Fast and Smaller, at About 118 Million Parameters
NVIDIA says its DLSS 5 rendering model is 2X faster, shrinking to about 118 million parameters, with Hogwarts Legacy support due on 5 November.
LightOn Releases ColGrep-Agent-2B, an Open Local Code-Search Agent That It Says Cuts Claude Code’s Tokens by a Third
LightOn's open 2B-parameter ColGrep-Agent searches code locally for coding agents; it says Claude Code used 34% fewer API tokens than with grep.
Meta Says It Turns Idle AI Inference Capacity Into Better Ads Recommendations
Meta's engineers describe a shared opportunistic capacity pool that uses idle inference capacity to rank more ads and serve stronger models.
Google Open-Sources ML Drift, the GPU Engine Inside LiteRT, Under Apache 2.0
Google has open-sourced ML Drift, the GPU engine inside LiteRT, under Apache 2.0. The 40%, 30% and 12% figures are Google's own claims; the old TFLite GPU delegate gets no new features.
Timer-M1 Preprint Says It Ranks First on Two Forecasting Benchmarks, With Its Authors’ Own Caveats
A preprint says Timer-M1, a forecasting model, ranks first on FEV and TIME. Its authors call the TIME margin over TimesFM-3 narrow. Not peer reviewed.
Underdog’s Saluki 27B Shrinks Qwen3.8-27B to 7.89 GB: Tool Calling Up on Its Own Test, Competition Maths Down
Underdog's Saluki 27B is a 7.89 GB, 2-bit version of Qwen3.8-27B. Underdog says it passes more tool-calling tasks than the full model on its own 120-task test but scores 15 to 18% lower on competition maths. What quantisation means, and what the numbers do not prove.
NVIDIA’s Jetson Kiosk Demo: A Coding Agent Puts a Vision Model on the Device
An NVIDIA tutorial shows OpenAI's Codex coding agent turning a Jetson Orin Nano into a self-starting kiosk that captions a live webcam feed with Google's small Gemma 4 E2B model, running on the device. What the demo shows, what "No Mac required" means, and why local inference matters.
Microsoft Execution Containers and AWS Strands Box Fence In AI Agents
Microsoft made its Execution Containers generally available on Windows 11 as it rebuilds Windows for local and cloud "hybrid" AI, and opened Surface Laptop Ultra pre-orders from $2,599. AWS open-sourced Strands Box, a sandbox that enforces rules such as "no git push" whatever the agent decides. What an enforced sandbox does, in plain words.
Personalised RAG, Memory and AI Agents: How a Hybrid Assistant Works
Update, 2 Nov 2026: This explainer has been revised. We removed an unsupported claim about measured gains from chatbot memory features, softened claims that RAG systems do...
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.