{"full_name":"Niko1221/Strata","owner":"Niko1221","name":"Strata","shard":"1","url":"https://github.com/Niko1221/Strata","description":"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.","homepage":"","topics":[],"tag_pages":[],"language":"C++","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/86886444?u=0252622cf8ec18e10cf16f39f288c16035be1251&v=4","created_at":"2026-09-24T16:40:20Z","pushed_at":"2026-11-16T08:45:12Z","metrics":{"stars":44681,"forks":4935,"watchers":213,"issues":2951,"prs":3066,"releases":68,"issues_open":741,"issues_closed":2210,"prs_open":765,"prs_closed":2266,"prs_merged":35,"discussions":0},"growth":{"day":{"stars":370,"forks":56,"base_day":"2026-11-15"},"week":{"stars":2454,"forks":318,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[42227,42671,43132,43422,43693,43998,44311,44681],"forks":[4617,4664,4721,4762,4797,4830,4879,4935],"watchers":[202,202,205,206,209,211,211,213],"issues_open":[null,null,628,645,659,686,711,741],"prs_open":[null,null,695,705,716,731,743,765]},"boards":{"daily":64,"weekly":56,"weekly_rate":198,"daily_forks":59,"daily_watchers":148,"new":5},"same_owner":[],"issues":[{"number":3330,"title":"[Other] Opinion: Strata app should be separate repo from Strata Engine","comments":51,"created_at":"2026-10-20T03:11:36Z"},{"number":2197,"title":"[Engine] Turing (sm_75): make the STRATA_SM75_PERF series the default, with expert mode 8 for i-quant packs","comments":47,"created_at":"2026-10-13T00:14:36Z"},{"number":3976,"title":"[Engine] Layer-major prefill on a CUDA layer split: 32K prompts 2.0x faster, 0.47x drive reads (Qwen3.8-Flash-Next, v0.2.4.2)","comments":30,"created_at":"2026-10-24T15:08:10Z"},{"number":4610,"title":"[Benchmark] record the host side in the standard report: measured PCIe per card, NUMA, memlock, GPU temperature and power","comments":27,"created_at":"2026-10-29T13:50:39Z"},{"number":4841,"title":"[Engine] Performance regression with engine 0.1.54/55 on 3090","comments":25,"created_at":"2026-10-31T18:01:04Z"},{"number":3463,"title":"[Engine] RX 7900 XTX (gfx1100) machine restarts under Strata serving (follow-up to #872)","comments":20,"created_at":"2026-10-20T15:15:03Z"},{"number":5160,"title":"[Engine] Intel Arc Pro B70 (SYCL): output corrupts to \"!!!!\" as prompts get longer, with drafting on or off","comments":19,"created_at":"2026-11-03T22:52:42Z"},{"number":5031,"title":"[Engine] Qwen3.8 Flash-Next on two mixed NVIDIA cards (RTX 4090 24 GB + RTX 4080 16 GB)?","comments":19,"created_at":"2026-11-02T20:32:57Z"}],"discussions":[],"latest_release":{"name":"Strata 0.2.14","tag":"v0.2.14","published_at":"2026-11-15T18:08:50Z","body":"# Strata 0.2.14: the prompt runs on Strata's own kernels on NVIDIA and AMD\n\nThe app and the Terminal are 0.2.14. Control and every engine package are 0.1.60. The update feed is sequence 125.\nThe Intel Arc engine stays at 0.1.59 in this release. The DGX Spark (linux-aarch64) engine stays at 0.1.59 too; its feed stays at sequence 123.\n\n## What changes for you\n\n- Nothing to do. Update as usual (see Updating below). Your models, chats and settings stay.\n- The engine reads your prompt with Strata's own code on NVIDIA and AMD cards, on Windows and Linux. Before, it used code taken from llama.cpp for this step. Answers can differ from 0.2.13 in some words; the tables below show how much.\n- There are no new settings.\n\n## Highlights\n\n- **Prompt reading on Strata's own kernels** on NVIDIA and AMD, Windows and Linux. A source build through setup builds the same way. `-DSTRATA_MMQ=ON` still builds the old llama.cpp path.\n- **Strix Halo (Windows), UD-Q4_K_XL, a 4,096-token prompt:** 2,621 ms (0.2.13: 2,689 ms). An 8,192-token prompt: 4,910 ms (0.2.13: 5,091 ms).\n- **RTX 4090, IQ3_S, a 20,000-token prompt:** 5,656 and 5,651 ms in two runs (0.2.13: 6,110 and 6,150 ms).\n- **RTX 5090, UD-Q4_K_XL, a 32,000-token prompt:** 7,870 tokens per second (0.2.13: 6,851).\n- **Mac (M5 Max), IQ3_S, a 7,755-token prompt:** 4,488 ms (0.2.13: 4,581 ms). Output, a 256-token story: 94.7 tokens per second (0.2.13: 92.8), the same text.\n\n## Speed against 0.2.13\n\nPrompt times in milliseconds (ms, fewer is quicker) or prompt tokens per second, and output in tokens per second (more is quicker). Numbers in brackets are 0.2.13 on the same PC. Each row names the engine build it was measured on: most rows ran on builds of 11-14, and \"build of 11-15\" is the 0.1.60 build of that morning. The NVIDIA and AMD engines that ship were built once more after it, with a fix that changes only a model split across two or more cards; the Mac engine that ships is the build of 11-15.\n\n| Machine, model | Prompt | Output | Engine measured |\n|---|---|---|---|\n| Strix Halo (Windows, 96 GB graphics memory), UD-Q4_K_XL | 4,096 tokens: 2,621 ms (0.2.13: 2,689). 8,192: 4,910 ms (0.2.13: 5,091). 32,000: 19,151 ms (0.2.13: 20,023) | all six kinds: 54.47 with the DFlash2 drafter. 0.2.13 on this PC still ran the MTP drafter from a setup of 11-04: 46.97. The 0.2.13 notes gave 49.1 with DFlash2 | build of 11-15 (4K, 8K); 32K and output on the build before it, same answers token for token |\n| Strix Halo (Windows), UD-Q4_K_XL, short prompts at 0.2.13's start line | 256 tokens: 408 ms (0.2.13: 2,010). 1,000: 877 ms (0.2.13: 3,112) | not measured | build of 11-14 (before Path A) |\n| Strix Halo (Windows), Gyro-S | 256 tokens: 485 ms (0.2.13: 736). 1,000: 1,098 ms (1,676). 4,096: 3,233 ms (4,323). 8,192: 6,598 ms (7,404). 32,000: 24,247 ms (28,027). Prompts of 26 to 64 tokens, 11 prompts together: 4,490 ms (4,436) | code and chat: 49.84 (0.2.13: 49.49) | build of 11-15 with the Gyro change, before the final |\n| RTX 4090 24 GB, IQ3_S | 4,096: 1,863 / 1,858 ms (0.2.13: 1,917 / 2,000). 8,192: 2,233 / 2,255 (2,380 / 2,404). 8,279: 2,695 / 2,757 (2,734 / 2,750). 16,884: 4,818 / 4,899 (5,212 / 5,050). 20,000: 5,656 / 5,651 (6,110 / 6,150). 32,000: 7,779 / 7,782 (8,295 / 8,300) | not measured | build of 11-14 with the prompt-cut fix, two runs each |\n| RTX 5090 32 GB, IQ3_S | tokens per second: 256: 1,347 (0.2.13: 1,196). 2,048: 3,800 (3,730). 8,192: 6,901 (6,517). 32,000: 7,899 (7,178) | chat 254.2 (274.0), code 304.8 (300.2), json 320.1 (316.0) | build of 11-14 |\n| RTX 5090 32 GB, UD-Q4_K_XL | tokens per second: 256: 988 (868). 8,192: 6,350 (5,945). 20,000: 7,710 (6,707). 32,000: 7,870 (6,851) | chat 148.6 (147.7), code 183.5 (183.9), json 160.5 (160.2) | build of 11-14 |\n| RTX 5070 Ti 16 GB, IQ3_S | tokens per second: 1,000: 372 (380). 8,192: 1,126 (1,125). 20,000: 1,408 (953) | chat 17.5 (19.4), code 21.8 (23.8) | build of 11-14 |\n| Mac M5 Max 128 GB, Q2_0 | 7,755 tokens: 3,673 ms (3,660) | 256-token story: 1","is_prerelease":false},"readme":true,"readme_zh":true,"news":[{"title":"Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s","url":"https://github.com/Niko1221/Strata","hn":"https://news.ycombinator.com/item?id=49953495","source":"Hacker News","lang":"en","date":"2026-10-04","points":940,"comments":420},{"title":"Strata: Qwen3.8-Flash-Next (125B Moe) on a 8GB+ Nvidia GPU","url":"https://github.com/Niko1221/Strata","hn":"https://news.ycombinator.com/item?id=49879253","source":"Hacker News","lang":"en","date":"2026-09-28","points":5,"comments":0},{"title":"Strata: Run a 125B-parameter AI model on a normal gaming PC","url":"https://github.com/Niko1221/Strata","hn":"https://news.ycombinator.com/item?id=49914465","source":"Hacker News","lang":"en","date":"2026-09-30","points":3,"comments":1},{"title":"[Is this the successor to Strata?] The case of the disappointing llama-modchip that supposedly runs DeepSeek-V4 without a GPU","url":"https://note.com/alpha2biker/n/nbe1f798e3754?hl=en","source":"note","lang":"en","date":"2026-11-10"},{"title":"[PLUS] KI-Revolution auf dem Gaming-PC: Was „Strata“ selbst aus älterer Hardware herausholt","url":"https://www.pcgameshardware.de/Kuenstliche-Intelligenz-Hardware-279517/Specials/strata-ki-test-125-milliarden-parameter-gaming-pc-1559417/","source":"PC Games Hardware","lang":"en","date":"2026-11-10"},{"title":"Is Strata a Game Changer for Local LLMs? Considering Large MoE and Adding GPUs with the RTX 5090","url":"https://note.com/gyokuto15/n/nc0d4f19b53fc?hl=en","source":"note","lang":"en","date":"2026-11-05"},{"title":"【strata】strataのDFlash2はあまり速くならなかった話【RTX3060×2】","url":"https://note.com/catap_art3d/n/n37bac2c745fc","source":"note","lang":"zh","date":"2026-11-03"},{"title":"Open-Source Fix Slashes DeepSeek V4.1 Startup Time on Gaming GPUs","url":"https://startupfortune.com/open-source-fix-slashes-deepseek-v41-startup-time-on-gaming-gpus/","source":"Startup Fortune","lang":"en","date":"2026-11-01"},{"title":"普通人真能跑1-bit大模型了！Strata 0.2.9发布：AMD/NVIDIA/Intel全平台狂飙，32K长文本提速88%","url":"https://www.sohu.com/a/1095449677_122066679","source":"搜狐","lang":"zh","date":"2026-10-31"},{"title":"本地AI大模型Strata 0.2.9发布：处理速度提升88%，支持1-bit DeepSeek！","url":"https://www.sohu.com/a/1095449300_122004016","source":"搜狐","lang":"zh","date":"2026-10-31"},{"title":"I tried running Strata on an old custom-built PC with a 14-year-old CPU by plugging in an RTX 3060","url":"https://note.com/alpha2biker/n/n677582d71634?hl=en","source":"note","lang":"en","date":"2026-10-30"},{"title":"Intel Arc B580 runs 125B AI model nearly 3x faster with XeStrata in new test","url":"https://www.notebookcheck.net/Intel-Arc-B580-runs-125B-AI-model-nearly-3x-faster-with-XeStrata-in-new-test.1434389.0.html","source":"Notebookcheck","lang":"en","date":"2026-10-26"},{"title":"Qwen3.8-Flash-NextがゲーミングPCで爆速に動く「Strata」登場","url":"https://pc.watch.impress.co.jp/docs/news/2145142.html","source":"PC Watch","lang":"zh","date":"2026-10-02"},{"title":"Strata：用显存+内存+硬盘协同调度，让普通电脑跑 1250 亿参数模型","url":"https://news.google.com/rss/articles/CBMiSEFVX3lxTE50dzhELWJBRXgxalVxRjdXQnd0c1I2MTNxZlFXS3NNY2hfNXFCcDRpQmZBRV9WXzNMcTlSNUFCYTZNRG0zTVJXMQ?oc=5","source":"黑海洋Wiki","lang":"zh","date":"2026-10-26"},{"title":"新浪网· - 手机新浪网","url":"https://news.google.com/rss/articles/CBMiY0FVX3lxTE5NN0IwcU0zX0hfeUJrTTY4blBoRlBkalVMeVVHcGthN25KVW9QM0M5SDhSWkgxcXlaS3QzcXlZZEt1YXRENFZNMnJDZjZ4YUJXeVdMMVo2ZDZ3LV95cFdDTnEtWQ?oc=5","source":"手机新浪网","lang":"zh","date":"2026-10-19"},{"title":"开发者Vibe两天产出Strata桌面管理端：本地大模型部署调参监控一站搞定","url":"https://news.google.com/rss/articles/CBMid0FVX3lxTE01MjczZDdpektQcGdLdU95OVduSC1saG1kTWc2ZGdOMWpvdHZCbGtmU2JKVlpGYmpNdFBQdHZGVVdSZGRHYUN0NTRIREhwSU5ZSElKdlVSbWkwbXMzWWFUR2YzVkwtOVlCLWViSHVRUHA4MENHVUJR?oc=5","source":"https://www.80aj.com/","lang":"zh","date":"2026-10-16"},{"title":"AI服务器需求推高存储成本：全球PC出货量下滑，DDR4平台获延长支持","url":"https://news.google.com/rss/articles/CBMiVEFVX3lxTFBnZXJWN3E5VDV3Njh1UHVvWmJfclJlZXVaU09QdGk5eGZNN2tQbWlsVnFrU2VuTW9TTHNPdTRwemY1RndSNkhoaFZ0UFlhMmQtYkFFVA?oc=5","source":"虎嗅","lang":"zh","date":"2026-10-10"},{"title":"Strata rewrites its GitHub history, 595 Claude co-author tags vanish","url":"https://news.google.com/rss/articles/CBMinAFBVV95cUxPWkNraFFtZTg5TkE5NmllMGVFQnFlaDJVemhvQ3RnZktEU2plRzJ0U1NfbUxTdExId09wWkVEWHdYUTFsdER0VkhoZS16ejk0cVJMMDhJRE9sNnBFdUluV2pLS0VJa202VXA0VUJWSEpmNXE4TV9UdV9STU9lWGhDS252bHYtdHRiLWp3MjVwakhtZHFRbnl4eDJlRjM?oc=5","source":"Pasquale Pillitteri","lang":"en","date":"2026-10-09"},{"title":"Strata 重写 GitHub 历史，595 条 Claude 署名消失，维护者确认重写","url":"https://news.google.com/rss/articles/CBMikAFBVV95cUxPWlB5YVhibklZcGRUaXRjYTV1VmQ5R2VKaXpzd200TnBXS0pvR3FBYl9EczF0UmdxV3FmRnk3Z3B2eE40OG1lektqaUtsMFNsMVM0TWs2aTliN01aY1hWSjdQRU5vUFBOeGVWOERVRC11eGxrV1RwSzJUaWxacGp6SFhPOXJvZlo3QmFpN0lLUVI?oc=5","source":"Pasquale Pillitteri","lang":"zh","date":"2026-10-09"},{"title":"12GB 显存显卡跑 125B Qwen3.8 模型：Strata 登场，单张 RTX 5070 跑出 94 词元 / 秒","url":"https://news.google.com/rss/articles/CBMiZEFVX3lxTFBZWUFQcG9uY09kSWNRUDgtYTJxWndGektjNHd4U3pTNk1JbXBUMlBxR2VGQ3dzUmc0UkNaUFNLMTdka3NQUm53ZkZpOHM0S0s1b1VrYXpiaGEwSUNNOE82dVN0QmU?oc=5","source":"17173","lang":"zh","date":"2026-10-06"},{"title":"Running a 125B-Parameter LLM on a Home PC: \"Strata\" Opens a New Frontier for Local AI","url":"https://news.google.com/rss/articles/CBMidkFVX3lxTE5KVDd3WFZNc2I0ZUpvWFNVLTNMQ0JQdW93TXdldGRVWF9iUmJPRkJZenh3eVBvN2dodDI0OG9WQWVTcnBaVzQ2QU9ncXhFYmRKR2MxTUxVWkM4YzJOeUtuTnVUWENoV2d4ZnE0M1NlQUYyZHdVN0E?oc=5","source":"BigGo Finance","lang":"en","date":"2026-10-05"},{"title":"Open-Source Tool Runs AI Locally","url":"https://news.google.com/rss/articles/CBMifEFVX3lxTE5yaHE0Y2N3WFRLQm9OYThqOVRRUl9jdkpuejFxbkkzdDZzZHN6YVYwR01BS0NQQ1RldDJ4RjVQb1dCb2VqNENSNUU3aktlaHZmZkFWLTVuSDVQSmlPOXRqUWM0YUV4WVZfcTg0akprM3BHM1ZVbXVtUmZIb1k?oc=5","source":"Open Source For You","lang":"en","date":"2026-10-05"},{"title":"'Strata' is an AI execution application that enables high-speed local execution of the quantized version of 125B's 'Qwen3.8-Flash-Next' on gaming PCs.","url":"https://news.google.com/rss/articles/CBMiakFVX3lxTE1tOGZzWjMxNHlVc3FVdEpJSlpUNEJJUTVnOXRTVU42ZWhmUWprWHNvZV9jMFd3X0l1bWNFNEdSQUE3NnF2NHZHM3pYRGpOWG5EdTNkSVJScV9kYkIxMlZLNWJESk16TWRQUWc?oc=5","source":"GIGAZINE","lang":"en","date":"2026-10-05"},{"title":"Strata lets a 125 billion parameter model run on a gaming GPU","url":"https://news.google.com/rss/articles/CBMikwFBVV95cUxNa2F0emhHU0c2Qkgxdmd2cVlHd0k5bG9rcVJCdFo2a3BPTkd4LXBGajNfRHZiNUtSRUtoeFpjeXJBNV9PcXB3NWswbmRmMmVMZmFNNXhVUE44cUJINTFDTUJBNGc5WGZXcS1oYUxWbXR4bVNEV2M5Q1Z1T1JnYk9nclRtVnllMEluT0hva3RGTm9rbWs?oc=5","source":"Startup Fortune","lang":"en","date":"2026-10-03"}],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}