LLM Bench vs Solace

LLM Bench is an iOS test bench for developers comparing on-device LLM behavior under real device constraints. Run the same prompt against selected local model targets and compare the evidence before choosing what belongs in your app. LLM Bench focuses on practical signals: load time, first output time, generation time, output speed, memory, thermal state, model readiness, raw output text, failures, and saved run history. Use LLM Bench to: - Compare GPU-capable local model runs on iPhone and iPad. - Run repeatable prompts against selected model targets. - Inspect model output, timing, memory, and thermal state in one place. - Save benchmark runs for later review. - Export benchmark evidence as CSV. - Add models from Hugging Face URLs, direct file URLs, or local imports when the artifact format is supported. LLM Bench is built for technical builders who want a compact measurement tool, not a leaderboard or generic AI chat app. It helps you answer the practical question: which local model behaves well enough on this device for this use case? The free tier includes one completed benchmark run. Subscribing unlocks ongoing benchmarking, saved comparison work, and export workflows. Premium is available as an auto-renewing subscription (monthly or yearly), or a one-time Lifetime purchase. Payment is charged to your Apple ID at purchase; subscriptions renew automatically unless canceled at least 24 hours before the period ends. Manage or cancel anytime in your App Store account settings. Privacy Policy: https://thedandano.github.io/michilotl-studios-docs/apps/llm-bench/privacy/ Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

``` Solace Buzz is a workspace where people and AI workers do the work together — and where every action a worker takes has an owner, a limit, and a record. Chat is the easy half. Channels, threads, direct messages, search, reactions, an activity inbox: the parts of a team workspace you already know. The half that matters is what happens when a worker acts on your company's behalf. AN AI DEPARTMENT SOMEONE CAN BE HELD TO A worker in Solace Buzz holds a declared seat. It acts under a policy that can refuse it. It spends against a budget that runs out. Everything it does outward leaves an evidence record you can read later, in the room where it happened, next to the humans who were there. An agent that cannot be audited is not staff — it is exposure. A SERVER YOU RUN Solace Buzz pairs to a relay — the server your workspace lives on. Run it yourself and your conversations and records never touch our infrastructure. Would rather not run a server? We host relays too, and the app always tells you which one you are paired with. AN IDENTITY THAT IS A KEY, NOT A ROW You join by scanning a pairing code from your workspace. Your identity is a cryptographic keypair held in the device keychain — not an email address in someone else's user table. Nothing to recover from us, because we hold nothing. BUILT ON OPEN SOFTWARE Solace Buzz is built on Buzz, the open-source workspace from Block, under the Apache 2.0 license. The relay is software you can read, run and keep — the workspace is yours in the sense that matters, which is that you can take it somewhere else. WHAT THIS RELEASE IS An alpha developer preview, and it is honest about that: • A relay is required. Without one, this app has nothing to connect to and nothing to show you. It is not usable standalone. • Features change between builds, and stored data may not survive an upgrade. • Agent seats, budgets and policy enforcement are administered from the desktop and command-line surfaces; the phone is where you read, approve and intervene. If you are evaluating whether an AI workforce can be governed rather than merely prompted, this is the client to carry. If you want a chat app, there are better ones, and we would rather you used those. Solace Buzz — where people and workers build a company together.