Strata: Qwen3.8-Flash-Next (125B Moe) on a 8GB+ Nvidia GPU

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 tokens per second. Measured on an RTX 5070 (12 GB), a Ryzen 5 7600 and 64 GB of RAM, the Q2_0 quantization writes at 90 tokens/s in short chat and 67 tokens/s at 128K context, while IQ3_S reaches 52 and 41 tokens/s respectively. The release also packages ISTA-DASLab's Coder variant, which keeps 91% of the full model's SWE-bench Verified score and 99% of LiveCodeBench, and UkisAI's Swift 1.5 fine-tune.

Run a 125-billion-parameter AI model on a normal gaming PC one NVIDIA card 12-24 GB + 64 GB of RAM · Windows or Linux · one click to install <sub A voxel pagoda garden, 1 shot prompt running on an RTX 5070 with Strata IQ3 S, 128K context · full video 49 s https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4 </sub Strata runs Qwen3.8-Flash-Next https://huggingface.co/Qwen/Qwen3.8-Flash-Next - a large, smart AI model that normally needs a server - on your own PC. It writes its answers at 60-95 tokens per second a token is about ¾ of a word : faster than you can read. - Free and open source. Jump to: How fast? how-fast-is-it · Which model? which-model-should-i-pick · Install install · Using it using-it · Problems? something-went-wrong · How it works how-does-it-work · All the details https://github.com/Niko1221/Strata/blob/main/docs/DETAILS.md Measured on an RTX 5070 12 GB , a Ryzen 5 7600 and 64 GB of RAM: | Size | Writes answers short chat | Writes answers 128K context | Reads your prompt | |---|---|---|---| | Q2 0 | 90 tokens/s | 67 tokens/s | 1,310 tokens/s | | IQ2 XS | 74 tokens/s | 60 tokens/s | 1,240 tokens/s | | IQ3 XXS | 62 tokens/s | 46 tokens/s | 1,110 tokens/s | | IQ3 S | 52 tokens/s | 41 tokens/s | 1,070 tokens/s | | Coder IQ1 M | 51 tokens/s | 44 tokens/s | 1,300 tokens/s | - Writes answers = how fast the reply appears tokens per second . - Reads your prompt = how fast it takes in what you send long documents, code, chat history , measured on a 32K-token prompt; a 4K prompt reads at 740-1,000 tokens/s. A 32K prompt takes about 25 seconds with Q2 0. A card with more VRAM is faster, because more of the model fits on the GPU: an RTX 3090 24 GB should do roughly 100-140 tokens per second. All measurements, long-context numbers and estimates for other cards are in the details https://github.com/Niko1221/Strata/blob/main/docs/DETAILS.md speed-measured . The size the same model, compressed more or less : | Model | RAM+VRAM Requirements | Speed | Quality | |---|---|---|---| | Q2 0 | 37.6 GB | fastest | good | | IQ2 XS | 39.2 GB | fast | better recommended | | IQ3 XXS | 47.0 GB | slower | great | | IQ3 S | 54.8 GB | slowest | best: matches the full model on the published tests original model only | Will it fit? Shard 1 is the part of the model that gets loaded when it starts: its experts go into your RAM , the rest onto your graphics card the second shard, a 29 GB lookup table, stays on the SSD . So it fits when your RAM is at least shard 1 + about 10 GB for Windows and your other programs. With 64 GB of RAM every size fits IQ3 S with little else open ; with 48 GB, Q2 0 and IQ2 XS. A bigger graphics card makes it faster, but it doesn't lower the RAM needed. The version: - Qwen3.8-Flash-Next - the original. - Coder https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF - ISTA-DASLab's coding version: half of the experts removed, keeping the ones that code, tool use and images need 91% of the full model's SWE-bench Verified score, 99% of LiveCodeBench, by its authors . One size IQ1 M: its experts stored like IQ3 S : shard 1 is 29.6 GB , so it fits a PC with 32 GB of RAM , runs 262K context on 64 GB, and reads long prompts the fastest of all. Weaker outside coding. - Swift 1.5 https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF - a fine-tune by UkisAI that thinks much shorter before answering, so you get the answer sooner, with about the same quality. Same speed per token, and about the same RAM as the same size of the original no IQ3 S . Its own license applies see its page . Not sure? Take IQ2 XS - or the Coder if you mainly write code, or have 32-48 GB of RAM. You can add another one later with SETUP.bat the same as START-HERE.bat --setup ; on Linux ./setup.sh --setup . You need: an NVIDIA RTX 30, 40 or 50 card with 12 GB of VRAM or more, enough RAM for the size you pick above , ~80 GB of free disk space an SSD makes the first start much faster , and Windows 10/11 or Linux. The only thing you install yourself is a current NVIDIA driver nvidia.com/drivers https://www.nvidia.com/drivers or the NVIDIA App . Everything else - Python, the engine, the model - is set up for you. Windows 1. Download this project https://github.com/Niko1221/Strata/archive/refs/heads/main.zip and unzip it or git clone it . 2. Double-click START-HERE.bat . 3. Answer a few questions - or just press Enter each time for the recommended choice: - Which model and size? The original or Swift 1.5, and Q2 0, IQ2 XS, IQ3 XXS or IQ3 S - see above which-model-should-i-pick - How much context? How much text it can keep in mind at once it suggests one for your card - Images? Whether it should also read pictures - Experimental speed projection? Off unless you say yes - read what it does https://github.com/Niko1221/Strata/blob/main/docs/DETAILS.md experimental-speed-projection-experimental-off-by-default first Then it downloads everything the model is ~70 GB, so the first time takes a while - you can stop and it picks up where it left off and starts the model . Your browser opens the Strata app at http://127.0.0.1:8080 . 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. That's normal - wait, and don't close the window. The window tells you what it is doing. Next time , just double-click START-HERE.bat again: it starts right away, nothing is downloaded twice. Close its window to stop the model. Updating: download the new version and unzip it anywhere or git pull , then run START-HERE.bat in it. The model files are kept in a Strata-data folder next to your Strata folder, so a new copy finds them and sets itself up the same way - nothing big is downloaded again. Linux: run ./setup.sh - same questions, same result. <sub The Strata app's Monitor left while a coding agent writes the pagoda garden from the video right </sub - In the browser: http://127.0.0.1:8080 - the Strata app it opens by itself when the model starts : Chat , a live Monitor of the model and your GPU/CPU/RAM, and About with the settings and addresses. - Chat in the terminal: .venv\Scripts\python chat.py - Your apps and coding agents: add it as an "OpenAI-compatible" provider with base URL http://127.0.0.1:8080/v1 , any API key and any model name. Apps that use Anthropic's API: http://127.0.0.1:8080/v1/messages . - Thinking: the model thinks before it answers. Choose off, low, medium or high - in the chat page menu, with /think low in chat.py , or with your app's "reasoning effort" setting. Off is fastest; high is best for hard questions. - Pictures: in the chat page click Picture ; in chat.py type /image <path ; in apps just attach them. - From your phone or another PC: START-HERE.bat --setup --host 0.0.0.0 --api-key <secret , then open the address the server window prints; see the details https://github.com/Niko1221/Strata/blob/main/docs/DETAILS.md using-it . - Experimental speed projection off by default : an experimental control vector that setup can turn on; it changes how the model answers - read what it does https://github.com/Niko1221/Strata/blob/main/docs/DETAILS.md experimental-speed-projection-experimental-off-by-default first. Good to know: it answers one request at a time. The first message of a chat is read in full about 1 minute per 30,000 tokens ; after that it keeps the conversation and reads only what is new, so follow-ups start in seconds. My PC froze, or got very slow, the first time Strata started. That's normal while it starts, most of all the first time. Strata loads 35-55 GB into your RAM, locks part of it for the graphics card, and works out how much of the model fits on your GPU. The mouse can freeze for a few minutes. Wait, and don't close the window. The next starts are much faster. Still frozen after 10 minutes? Restart the PC, close other programs browsers use a lot of RAM and try again. If it keeps happening, pick a smaller size Q2 0 or IQ2 XS . It stopped while downloading or installing. Run START-HERE.bat again. It continues where it stopped. It says the NVIDIA driver is too old. Update it NVIDIA App or nvidia.com/drivers https://www.nvidia.com/drivers , restart the PC, and run START-HERE.bat again. It says port 8080 is already in use. Strata is already running. Look for its window. It's very slow and the disk light keeps blinking. Your PC is out of free RAM. Close other programs, or pick a smaller size Q2 0 or IQ2 XS . An answer stopped with "the engine stopped unexpectedly". Usually not enough RAM on Linux the system then stops the engine . Just send your message again: Strata starts the engine by itself. If it keeps happening, close other programs or pick a smaller size. It says the prompt exceeds the context. The conversation is longer than the context you chose. Start a new chat, or run SETUP.bat and pick more context. Still stuck? Look in the full troubleshooting table https://github.com/Niko1221/Strata/blob/main/docs/DETAILS.md troubleshooting , or open an issue and attach strata-<model .log from the Strata folder. Models like this one normally run on servers with hundreds of gigabytes of graphics memory. Your graphics card has 12-24 GB. Strata makes it fit by sharing the work across your whole PC - the same idea as a kitchen, where the things you use all the time stay on the counter and the rest waits in the pantry. - The model is a team of 24,576 small specialists "experts" , and each word it writes needs only 10 of them. So it doesn't have to have all of them on the graphics card at once. - Your graphics card does the part of the work needed for every word, and keeps the few thousand experts that are asked most often. It keeps learning which ones those are while you use it. - Your RAM holds every expert. When a word needs one the card doesn't have, your processor works on it - at the same time as the graphics card, so neither waits for the other. - Your SSD holds a big lookup table; the model only reads a few small rows of it per word. - Guess, then check. A small, fast helper built into the model guesses the next few words, and the big model checks all the guesses in one go. It keeps the ones it agrees with and writes the next word itself - so one step often produces several words. The helper only guesses - the big model decides every word - so you get the same quality answer, 1.6-1.8x sooner. - Long texts are read in big pieces up to 8,192 tokens - pieces of words - at a time , which is why a long document or code base is read at over 1,000 tokens per second. Want the full picture? The details https://github.com/Niko1221/Strata/blob/main/docs/DETAILS.md how-it-works explain every part and its numbers, and the paper https://github.com/Niko1221/Strata/blob/main/docs/paper/Strata-Paper.pdf tells the whole story, with the measurements behind it. - Model: Qwen3.8-Flash-Next https://huggingface.co/Qwen/Qwen3.8-Flash-Next by the Qwen team; compressed versions by ISTA-DASLab https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF ; Swift 1.5 https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF by UkisAI. Their licenses apply to the model files. - Built with parts of llama.cpp / ggml https://github.com/ggml-org/llama.cpp MIT . Ideas from Splash https://github.com/incoai/splash , ninfer https://github.com/Neroued/ninfer and HyperQwen https://github.com/syv-ai/HyperQwen . More in the details https://github.com/Niko1221/Strata/blob/main/docs/DETAILS.md credits-and-licenses . Strata is open source under the MIT License https://github.com/Niko1221/Strata/blob/main/LICENSE . A few parts carry their own licenses: third party/ggml MIT, llama.cpp / ggml , the web app's font SIL Open Font License 1.1 and the experimental speed projection's vector in data/experimental-speed-projection Qwen Community License 1.0, from the model's activations . The models are not part of this repository; each model's own license applies to its files.