A developer known as Niko1221 has published Strata, a repository showing that the 125B-parameter Qwen 3.8 Flash Next model can run on a single consumer RTX 4090 at roughly 100 tokens per second. The s…
Strata v0.1.38 runs Qwen3.8-Flash-Next, a 125B mixture-of-experts model, on a gaming GPU at 94 tokens per second without a server, according to byteiota. The report attributes the feat to the model's …
The open-source project Strata, from developer Niko1221, runs a 125-billion-parameter Qwen3.8 mixture-of-experts LLM on gaming-PC hardware by treating VRAM as a cache and keeping the full expert set i…
Open source inference engine Strata, built by a developer known as Niko, runs Alibaba's 125 billion parameter Qwen3.8-Flash-Next mixture of experts model on a single consumer GPU with as little as 8GB…
A homelab test on an i5-12600K with 64 GB DDR5 and an RTX 4070 12GB found the narrow inference runtime Strata generated 512 tokens at 53.2 tok/s with 60,000 tokens of context on the 125B-parameter Qwe…
Strata launched a self-contained analytics harness that runs on a laptop in about a minute via a single curl install script, the company announced. The image bundles a PostgreSQL instance, generates i…
Ajo, a former Netflix engineer, launched Strata, an early-beta semantic layer that includes dashboards, subscriptions, and Google Sheets exports and can be driven by agent conversation or MCP. Strata …
Strata, an open-source tool from developer Niko1221, runs the 125-billion-parameter Qwen3.8-Flash-Next model on a single NVIDIA GPU with 12-24 GB of VRAM and 64 GB of RAM, generating answers at 60-95 …
Enterprise software lacks a field to record both who acted and under whose authority when an AI agent performs an operation, conflating the agent's identity with the human's or service account's. Okta…
Stele has open-sourced Strata, a session infrastructure that normalizes coding agent trajectories into a unified CLI and TypeScript API. It supports multiple agents including Claude Code, Codex, and C…
Gartner projects the average Fortune 500 company will grow from fewer than 15 AI agents in 2025 to over 150,000 by 2028, while fewer than half of security leaders can identify all active agents in the…
Eighty-eight percent of enterprises have reported at least one security incident tied to AI agents, and 61% of those trace back to over-permissioned credentials, according to a report cited in a new a…
A review of Cube.dev by Strata, a competing semantic layer builder, finds that Cube has evolved into a full BI solution with workbooks, dashboards, and AI chat interfaces. The open-source version was …
Highloop LLC's Strata app delivers AI-powered backcountry route planning with a plain-English safety verdict of go, watch, or avoid, drawing on avalanche bulletins, slope data, and live weather via An…
Anthropic's Claude model, writing as Fable 5, argues that the universal semantic layer is a rational response to metric drift in enterprises but has a structural weakness: generic protocols like SQL c…