Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
{
"fx01": "will stop running and be removed.",
"fx02": "Downloaded, not loaded. Open Models to load it.",
"fx03": "{0} lines added, {1} removed",
"fx04": "Edited {0} files",
"fx05": "Drop files to add them",
"fx06": "Pictures and text files",
"fx07": "Keep goal",
"fx08": "Remove goal",
"fx09": "The assistant stops working towards it. Your chat and files stay as they are.",
"fx10": "This model can read pictures, but the engine installed here does not include the picture reader yet, so Read pictures is off. Update the engine in Settings → About to turn it on.",
"fx11": "Showing the values of your tuning '{0}'.",
"fx12": "Your tuning '{0}' sets",
"fx13": "was {0}",
"fx14": "· {0} RAM",
"fx15": "The message was not cancelled",
"fx16": "Extra settings for the program",
"fx17": "Draft it with AI",
"fx18": "Thinking time",
"fx19": "Writing time",
"fx20": "tokens/s",
"fx21": "% of context",
"fx22": "This page asks for files from the internet, which the preview does not load, so it may look incomplete. View code shows exactly what was written.",
"fx23": "Keep A",
"fx24": "Keep B",
"fx25": "Took",
"fx26": "Variation",
"fx27": "Changed",
"fx28": "Nothing",
"fx29": "Both versions are ready. Compare A and B, then keep one.",
"fx30": "The assistant is still answering",
"fx31": "Send your message when it has finished.",
"fx32": "The message was not queued",
"fx33": "Scroll to the latest message",
"fx34": "Remove task",
"fx35": "Start a new conversation; keep this one",
"fx36": "Have the assistant write a plan first; nothing runs until you approve it",
"fx37": "Search the web, read the pages and answer with sources",
"fx38": "Copied",
"fx39": "Response",
"fx40": "Message",
"fx41": "PDF added",
"fx42": "Select the text and copy it with Ctrl+C.",
"fx43": "{0} is in this chat. Ask about it in your next message.",
"fx44": "The engine is ready.",
"fx45": "Next: pick a model.",
"fx46": "Downloading the engine",
"fx47": "You can close Strata; it continues where it stopped.",
"fx48": "Welcome to Strata",
"fx49": "Looking at your graphics card…",
"fx50": "Strata found your graphics card:",
"fx51": "{0} cards found. Strata uses the first one for the engine; change it later in Settings.",
"fx52": "Strata did not recognise a supported graphics card.",
"fx53": "To run models on it, Strata needs one download:",
"fx54": "The engine for this card",
"fx55": "The engine needs about {0} GB of free space on this drive and only {1} GB is free. Free some space, then continue.",
"fx56": "It comes from Strata’s own update server and is checked before it is used. Your models and chats are never touched by it.",
"fx57": "Strata could not reach github.com. Check your connection and try again, or download the engine file on another PC and choose it here.",
"fx58": "The engine installed here is for another make of graphics card.",
"fx59": "Strata can’t pick an engine for this PC from its update list.",
"fx60": "Continue without an engine",
"fx61": "The download stopped. Continue picks it up where it stopped.",
"fx62": "This is a very large model. The download is {0} GB and it needs about as much free disk space. It runs on one 12 GB graphics card with 46 to 64 GB of RAM, slowly: about 5 to 7 words a second. What does not fit in memory is read from your SSD, so an NVMe drive matters.",
"fx63": "You can stop the download and continue later; it picks up where it stopped. Strata warns you here but never blocks you.",
"fx64": "Faster",
"fx65": "Full quality",
"fx66": "Default (Faster on this PC)",
"fx67": "Default (Full quality on this PC)",
"fx68": "Faster (default on this PC)",
"fx69": "Full quality (default on this PC)",
"fx70": "Faster long prompts",
"fx71": "Faster answers on Radeon RX 9000 / AI PRO R9700",
"fx72": "DeepSeek speed-ups",
"fx73": "Reads very long prompts faster by approximating part of the work. Off by default: answers about long documents can miss or mix up details.",
"fx74": "Shares the work between the graphics card and the processor in a way that makes answers faster on these cards. Turn off to go back to the previous setting, which is slower.",
"fx75": "Reads long prompts faster and loads the parts of the model it needs faster. Turn off if DeepSeek stops working or its answers look wrong; it then runs as in version 0.2.6.",
"fx76": "On (recommended)",
"fx77": "This is a very large model. The download is {0} GB and it needs about as much free disk space. It runs on NVIDIA RTX 30, 40 and 50 cards, on a Radeon AI PRO R9700 (Linux) or on a Ryzen AI Max / Strix Halo PC (Windows); how fast it is depends on the memory and card (the line below says what to expect on this computer). What does not fit in memory is read from your SSD, so an NVMe drive matters.",
"fx78": "Not tested yet. A context this long takes graphics memory from the model and reads long prompts slowly.",
"fx79": "Off (recommended)",
"fx80": "Needs about {0} GB of free disk space. What does not fit in memory is read from your SSD.",
"fx81": "{0} RAM + VRAM, plus about {1} GB of disk",
"fx82": "Faster answers on 12 GB NVIDIA cards",
"fx83": "Prefers the parts of the model already on the graphics card, which makes answers faster on 12 GB cards. Off by default: in long agent sessions it can repeat itself and give weaker results. Turn on if you mostly chat and want the speed."
}