Overview

** The model can chat, generate code, and analyse images, all without a server-side backend.

System Requirements

Selecting the Appropriate Model Size

Available RAM Recommended Variant Reason
32 GB Coder Fits within memory limits while retaining code-generation ability.
48 GB IQ2_XS (or faster Q2_0) Balances speed and memory usage.
64 GB Any size, including the largest Q2_0 engine No constraints.

Performance Benchmarks on Consumer GPUs

**

Model Write Speed Prompt Read Speed
Q2_0 94 tokens/s 2,650 tokens/s
IQ2_XS 79 tokens/s 2,090 tokens/s
IQ3_XXS 62 tokens/s 1,750 tokens/s
IQ3_S 53 tokens/s 1,620 tokens/s
Coder 55 tokens/s 2,180 tokens/s

**

Model Write Speed Prompt Read Speed
Q2_0 60 tokens/s 1,160 tokens/s
IQ2_XS 52 tokens/s 1,110 tokens/s
Coder 44 tokens/s 1,420 tokens/s

Installation Process

AI-Assisted One-Click Install

If you use an AI coding assistant (Claude Code, Cursor, Codex, GitHub Copilot, etc.), paste the following prompt:

Set up Strata on this PC for me: https://github.com/Niko1221/Strata – follow docs/AI_SETUP.md in that repository.

The assistant will:

  1. Detect GPU, RAM, and storage.
  2. Download the appropriate engine version.
  3. Configure environment variables and launch scripts.

Operating Strata

  • Launch the Strata executable.
  • Use the built-in console or integrate with your IDE via the provided API key.

Common Issues & Troubleshooting

  • Driver incompatibility – Update to the latest NVIDIA/AMD driver and restart the system.

Frequently Asked Questions

Q: Does the model send data to the cloud? A: No. All inference runs locally on your hardware.

Q: Can I run multiple GPUs simultaneously?** A: Yes. Strata supports multi-GPU configurations; the installer will detect additional cards and distribute the workload.

**

It checks your graphics card, RAM and disk and picks the model that fits. Then it installs and starts it and tells you how to connect your apps. AI tools can also install, start and stop Strata through its MCP server.

Manual installation steps

Download Strata and unzip it (or git clone it). Windows: double-click START-HERE.bat. Linux: run ./setup.sh in the Strata folder. The steps are the same for NVIDIA and AMD. The installer finds your card and sets up the right engine for it. It asks you a few questions: which model and which size, how much context (how much text the model keeps in mind), whether it should read pictures. Press Enter each time for the recommended answer. Then it downloads the model (about 70 GB) and starts it. If the download stops, run it again: it continues where it left off. While the model starts, your PC can be slow or stop responding for 1-3 minutes (longest the first time). Strata loads 35-55 GB into your RAM and locks part of it for the graphics card. This is normal. Wait, and don't close the window. The window shows what Strata is doing. Next time, run START-HERE.bat (or ./setup.sh) again. It starts right away and downloads nothing twice. Close its window to stop the model. UPDATE.bat (./update.sh) updates Strata without starting it.

Selecting the Appropriate Model Size

RAM-based model recommendations

RAM available Recommended model(s)
32 GB Coder – it fits 32 GB, and it is made for code (with a 24 GB card, Q2_0 and IQ2_XS run too)
48 GB IQ2_XS (or Q2_0, the fastest) – the larger sizes do not fit
64 GB IQ2_XS (recommended), or IQ3_XXS / IQ3_S – every size fits; IQ3_S is the best and the slowest
96 GB or more IQ3_S, or Unsloth's UD-IQ4_XS (~4-bit) – room for the largest sizes with everything else open

Coder: a coding version with half of the experts removed. It reaches 91% of the full model's SWE-bench Verified score (measured by its authors) and fits 32 GB of RAM. It is weaker outside code, including Chinese and other CJK text (#438). For those, take Q2_0, IQ2_XS or IQ3_S, which keep every expert.

Swift 1.5: a fine-tune that thinks for a much shorter time before it answers. You get the answer sooner, at about the same quality.

Unsloth UD-IQ4_XS: Unsloth's ~4-bit version, between IQ3_S and UD-Q4_K_XL in quality. A 94 GB download. With less than ~80 GB of RAM, Strata reads part of it from the SSD while it answers, so it is slower there (an NVMe SSD helps).

Unsloth UD-Q4_K_XL (experimental): the closest to the full model. But Strata reads most of it from the SSD while it answers, so it writes only 7-8.5 tokens/s on a 64 GB PC.

OrcaRouter's Uncensored IQ3_XXS: you set it up by hand. It is not in the installer's menu.

Alternative and experimental models

The descriptions above cover the main experimental variants. For a complete list of sizes, downloads and fit-rules, see docs/MODELS.md. To add another model later, run SETUP.bat (Linux: ./setup.sh --setup).

Operating the Strata Application

Web UI and monitoring

It has Chat, a live Monitor of the model and your GPU/CPU/RAM, and About with the settings and addresses.

API endpoints and integration

Any API key and any model name work.

Codex CLI and other apps that use the OpenAI Responses API: /v1/responses (setup).

Configuring reasoning effort and image input

Thinking: choose off, low, medium or high in the chat menu or in your app's “reasoning effort”. Off is the fastest. High is best for hard questions. Pictures: say yes to “Images?” in setup. Then click Picture in the chat, or attach pictures in your app. AMD cards read pictures on Linux through the processor; on Windows they can't yet.

Parallel request handling and long prompts

One request at a time: by default Strata answers one request, and the others wait. To answer several at once, set "parallel": 2 (BATCHING.md). On a 12 GB card this makes each answer slower. Long prompts: Strata reads the first message of a chat in full, about 1 minute per 30,000 tokens. Follow-up messages start in seconds.

Common Issues and Troubleshooting

My PC froze the first time Strata started. This is normal while it loads the model. Wait, and don't close the window. Still frozen after 10 minutes? Restart the PC, close other programs and try again, or pick a smaller size. It stopped while downloading or installing. Run START-HERE.bat (or ./setup.sh) again. It continues where it stopped. Your PC does not have enough free RAM. Close other programs (browsers use a lot), or pick a smaller size (Q2_0 or IQ2_XS). It says port 8080 is already in use. Strata is already running. Look for its window.

Frequently Asked Questions

It needs 12 GB of VRAM or more.

** Your RAM decides which model fits. 64 GB runs every size.

** AMD cards read pictures on Linux through the processor; on Windows they can't yet.

** Always set a key.