# AI use cases for Strata (Niko1221/Strata) Repo: [Niko1221/Strata](https://github.com/Niko1221/Strata) | Use cases: 3 | Page: https://dedupedai.com/use-cases/niko1221-strata/ Strata runs large open models such as Qwen3.8-Flash-Next, Qwen3.6-35B-A3B and DeepSeekV4.1-Flash on your own computer, as a desktop app or a terminal app, with no account. It picks quantized model packs that fit your hardware, reads what does not fit in memory from your SSD, and exposes OpenAI- and Anthropic-compatible APIs so Claude Code, Codex CLI, OpenCode and other tools can use the local model. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run a frontier-size open model locally from the terminal: https://dedupedai.com/use-cases/niko1221-strata/run-a-big-model-locally-with-strata/ - Point Claude Code or Codex at a local model with strata connect: https://dedupedai.com/use-cases/niko1221-strata/use-a-local-model-in-claude-code-via-strata/ - Run DeepSeekV4.1-Flash on a 12 GB GPU by streaming from SSD: https://dedupedai.com/use-cases/niko1221-strata/run-deepseek-v4-1-from-your-ssd/ ## How to run a frontier-size open model locally from the terminal with Strata Repo: [Niko1221/Strata](https://github.com/Niko1221/Strata) | Difficulty: Beginner | Time: 1 hour | Basis: From the README Install Strata, let it pick a model pack for your hardware and start chatting, with no account. **Who it is for:** A developer with a gaming GPU who wants a capable local model for private work. **The problem:** Big open models usually need manual quantization choices, engine builds and more memory than you have. **The outcome:** A local model running on your own GPU, picked to fit your memory, with live model and hardware stats. ### Steps 1. On Linux or Mac run `curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh` 2. On Windows run the PowerShell installer from the README, then open a new terminal 3. Run `strata launch` and follow the prompts to download and start a model 4. Check the Models section and docs to choose a pack that fits your memory 5. Prefer a window? Use the desktop app installer instead ### Prompt to paste into your agent ```text Install Niko1221/Strata on this machine, check my GPU and RAM, recommend a model pack from the README's Models section that fits, then run strata launch and confirm the model answers a test prompt. ``` ### Caveat Model downloads are large and speed depends heavily on your GPU and RAM; check the hardware table before choosing. Risk, remote script: The installer downloads and runs install.sh from the latest release; read it first if you prefer. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/niko1221-strata/run-a-big-model-locally-with-strata/ ## How to point Claude Code or Codex at a local model with strata connect with Strata Repo: [Niko1221/Strata](https://github.com/Niko1221/Strata) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Use Strata's OpenAI- and Anthropic-compatible APIs so your coding agent runs on your own GPU. **Who it is for:** A developer who wants coding agent help on private code without sending it to a cloud API. **The problem:** Coding agents default to cloud models, which cost money per token and send your code off the machine. **The outcome:** Claude Code, Codex CLI or OpenCode talking to a model served by Strata on your machine. ### Steps 1. Install Strata and start a model with `strata launch` 2. Run `strata connect` to see the setup instructions for your tool 3. Apply the settings for Claude Code, Codex CLI, OpenCode or another listed tool 4. Pick the Coder pack from the Models docs if you mostly write code 5. Run a small coding task and compare speed and quality with your cloud model ### Prompt to paste into your agent ```text Using Niko1221/Strata, start a local model, run strata connect, and configure to use it following the printed instructions. Then run a small refactor on and report tokens per second. ``` ### Caveat Local models are slower than cloud APIs on most consumer GPUs; the README lists 4 to 25 tokens per second for DeepSeekV4.1 on single cards. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/niko1221-strata/use-a-local-model-in-claude-code-via-strata/ ## How to run DeepSeekV4.1-Flash on a 12 GB GPU by streaming from SSD with Strata Repo: [Niko1221/Strata](https://github.com/Niko1221/Strata) | Difficulty: Advanced | Time: half a day | Basis: From the README Plan and launch the IST-DAS 2.00 bpw set, which reads what does not fit in memory from disk. **Who it is for:** An enthusiast with an RTX 3060 or 5070 and a large SSD who wants to try a top open model at home. **The problem:** A model of this size does not fit in consumer VRAM and RAM at all with normal tools. **The outcome:** DeepSeekV4.1-Flash running locally at single digit to low double digit tokens per second, according to the README table. ### Steps 1. Install Strata as in the quick start 2. Make sure you have about 265 GB of free disk for the 2.00 bpw set 3. Preview the setup with `strata launch --family deepseek41 --model ist-das-2.00bpw --plan` 4. Run the launch without --plan to download the files and the DeepSeek engine and start the model 5. Compare your speed with the README's measured hardware table ### Prompt to paste into your agent ```text Check whether this machine can run DeepSeekV4.1-Flash with Niko1221/Strata: report free disk, GPU and RAM, run the --plan command for the ist-das-2.00bpw set, and only start the full download if there is at least 265 GB free. ``` ### Caveat Supported for this model on NVIDIA RTX 30, 40 and 50 (Windows and Linux) and AMD Radeon AI PRO R9700 (Linux) only. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/niko1221-strata/run-deepseek-v4-1-from-your-ssd/