Observed Signal · Aug 30, 2026 · Technical Release · Source: DEV Community · Impact: 2/5 · Sentiment: Positive
Flash Onyx 2.2 Released, Finishes Model Improvements
Flash Onyx 2.2, a new version of the Flash Onyx model by the author 'Natuworkguy', is published and available via Ollama. The release ships in two sizes (12b for consumer hardware and 31b for GPU-equipped machines) and focuses on improving request comprehension, producing correct concise answers, automatic stack selection, safer and more accurate Manim animation code generation, and better game-development patterns. Sampling and context settings were adjusted (temperature 0.7→0.6, min_p 0.0→0.05, num_ctx 32768→65536). The post includes install/pull commands for Ollama, recommended MODEL env settings, and an install script link. The author invites feedback and notes that future work (2.3) will address any failures encountered when using 2.2.
A developer-focused release of a locally runnable LLM with increased context window and sampling refinements; relevant to engineers and generative-AI tooling but not a major platform-level change for the AdTech industry.
Track Ollama Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your Polaris7 workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Flash Onyx 2.2 is published and available on Ollama.
- The model is offered in two sizes: 12b (runs on normal consumer hardware) and 31b (requires a real GPU).
- Sampling and context configuration changes: temperature 0.7 -> 0.6; min_p 0.0 -> 0.05; num_ctx 32768 -> 65536.
- Primary improvements include better understanding of requests, automatic stack selection, improved Manim code generation, and higher completion quality.
- Install/pull instructions provided (ollama pull and an install script at flashproject.dev).
Connected Companies & Entities
“Flash Onyx 2.2 is live on Ollama.”
“It's the model behind FLASH CLI, my local terminal agent.”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Flash Onyx 2.2: Local Model for Law and Game Feel
Flash Onyx 2.2 is a development update for a local-first agent shell (Flash Onyx) built around gemma4 configured as an engineering agent that runs fully on a 16 GB laptop GPU at single-digit tokens per second. Version 2.2 expands the system-prompt domains beyond code into legal and game-design guidance, with strict rules (e.g., refuse invented citations, jurisdiction-first for law; game feel heuristics for games). The author compressed prompt text to reduce per-conversation prefill cost, tuned sampling (temperature moved from 0.7 to 0.6 and min_p from 0 to 0.05), and increased context window to 65536 after probes showed 32k/64k/128k used ~8.1–8.2 GB GPU memory. Build tooling now injects the repo license into models; Onyx 2.2 is not yet published but is planned as Natuworkguy/flash-onyx-2.2 in 12b and 31b variants.
Nano Banana 2 (Gemini 3.1 Flash) Model Review
Anthropic shipped a /loop feature for Claude Code that schedules agent tasks (every few minutes, hourly, or at set times). The newsletter argues /loop supplies the missing “heartbeat” or proactivity primitive that, when combined with memory (e.g., Open Brain) and tool integrations (MCP, external tools), turns chatbots into autonomous, delegable agents — described as an "OpenClaw you control." The author outlines layered examples showing capability changes as memory, proactivity and tools are stacked, discusses architectural separation between scheduling and memory, and provides two hands‑on guides: one to wire a /life‑engine skill with Claude Code, MCP and Telegram using /loop, and a second to convert agent briefings into short animated videos. Use cases range from energy tracking to sales pipelines, and the piece highlights gaps, security considerations, and why terminal-based tooling delivers early advantage.
Google launches Gemini Omni 1.1 Flash
Google has rolled out Gemini Omni 1.1 Flash, an updated AI video model that adds 4K upscaling, scene expansion, explicit start/end frame control and longer reference-video support. The model is available via the Gemini API, Agent Platform API and Google AI Studio; Ultra, Plus and Pro users can also access it in Google Flow and the Gemini app. Gemini Omni 1.1 Flash can extend videos in 10‑second increments up to 40 seconds while using up to 10 seconds of preceding context, and it supports reference videos up to three seconds for character and motion consistency. Pricing varies by output resolution (360p to 4K) and the release includes lower-cost lightweight previews to reduce generation costs during prototyping.
Receive all future signals for Ollama & competitors in your briefing
Never miss material M&A deals, leadership changes, account wins, or product rollouts. Polaris7 monitors 20,000+ primary sources 24/7, delivering verified telemetry directly into your executive briefing.