Qwen3.8 Flash at 74 tok/s on a single DGX Spark / GB10. vLLM + MTP recipe, 212 tok/s at 8 streams.
☆82Sep 29, 2026Updated last month
Alternatives and similar repositories for qwen3.8-Flash-DGX-UltraFast
Users that are interested in qwen3.8-Flash-DGX-UltraFast are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark (fork)☆50Oct 22, 2026Updated 2 weeks ago
- recipe for running Qwen3.8-Flash-Next on a single DGX Spark☆508Updated this week
- qwen38-flash-next recipe for solo GB10☆171Oct 30, 2026Updated last week
- 改善 Qwen3.8 輸出模板（chat template）：修工具呼叫格式、繁中輸出與思考標籤問題☆28Oct 28, 2026Updated last week
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆627Oct 4, 2026Updated last month
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆16Updated this week
- An GB10-optimized inference engine☆129Oct 28, 2026Updated last week
- An open-source Perplexity analogue for Research Data Management based on Perplexica☆11Oct 13, 2024Updated 2 years ago
- Based on assafelovic/gpt-researcher - Modified to support local Ollama models☆16May 15, 2024Updated 2 years ago
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRg…☆561Updated this week
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆97Nov 1, 2026Updated last week
- Live per-node GPU, host, and vLLM stats for DGX Spark clusters, in your terminal☆17Updated this week
- SearXNG-Crawl4AI is an open-source search and crawling tool based on SearXNG and Crawl4AI, serving as an open-source alternative to Tavil…☆17Oct 27, 2025Updated last year
- Docker configuration for running VLLM on dual DGX Sparks☆2,477Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- An opinionated framework for deploying a fully self-hosted AI chatbot interface with integrated document processing, document search, and…☆13Feb 28, 2026Updated 8 months ago
- Qwen3.8-27B on DGX Spark (GB10): SGLang + NVFP4 + DFlash2. Measured recipe, benchmark harness, and the traps that cost real time.☆25Aug 25, 2026Updated 2 months ago
- Make your terminal string output even more beautiful 💖☆11Jul 27, 2025Updated last year
- Impulse by Velocity: run AI models on your own computer, on Windows and Linux. Load any GGUF model and chat with web search, files, chart…☆34Updated this week
- Archived fork of antirez/ds4 for GB10 DSpark — continues as Athena: github.com/xangel82/Athena-Engine☆28Oct 30, 2026Updated last week
- Scitrera builds of various CUDA containers for version consistency, starting primarily with NVIDIA DGX Spark Containers☆41Aug 21, 2026Updated 2 months ago
- 在瀏覽器選一個 Markdown vault，用 Jev 逐篇判斷該掛哪些標籤。高信心自動採納，其餘人工審核，可回滾☆10Sep 24, 2026Updated last month
- A local reverse proxy that records every LLM request/response to SQLite. No cloud, no data leaving your machine.☆15Mar 1, 2026Updated 8 months ago
- LLM-Training-API: Including Embeddings & ReRankers, mergekit, LaserRMT☆28Feb 18, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆17Sep 6, 2026Updated 2 months ago
- Bleeding-edge ComfyUI for NVIDIA DGX Spark (GB10/Blackwell/sm_121a). CUDA 13 + SageAttention v3 (sm_121a) + NVFP4 + 14 custom-node packs …☆89Oct 6, 2026Updated last month
- Production-ready Model Context Protocol server for Threads.com API. Features rate limiting, caching, webhooks, and full TypeScript suppor…☆18Apr 15, 2026Updated 6 months ago
- A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively☆128Feb 22, 2026Updated 8 months ago
- Turn orbit videos (including AI-generated ones) into Gaussian Splats, 100% locally in the browser with WebGPU.☆38Oct 20, 2026Updated 2 weeks ago
- Diablo II: Resurrected, native on Apple silicon: ray traced, rebuilt by MetalFX, smooth at 60 fps. Bring your own Switch copy of the game…☆31Updated this week
- Text to handwritten pages written in python. 12 fonts, 12 papers, PNG/PDF output.☆23Updated this week
- Ion is a zero-install, browser-native coding agent.☆41Oct 14, 2026Updated 3 weeks ago
- C# Dictionary Backed By FASTER☆18Dec 8, 2022Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Turn any documentation website into AI/LLM-ready Markdown in seconds.☆10Mar 13, 2026Updated 7 months ago
- wicket-js makes it easy to write and handle custom JavaScript and jQuery from within Wicket Components and Behaviors.☆10Mar 30, 2015Updated 11 years ago
- ☆10Aug 6, 2018Updated 8 years ago
- Don't install this on anything other than the inkPalm 5 and *maybe* the MiReader☆10Jun 20, 2021Updated 5 years ago
- Privacy-first, local-first research notebook for macOS & Windows — chat with your own PDFs, Office docs & web pages and get cited answers…☆20Oct 14, 2026Updated 3 weeks ago
- ☆12Mar 31, 2025Updated last year
- Local AI proxy for Cline, Continue, Aider, Ollama, LM Studio, and OpenAI-compatible tools. Reduce repeated tokens, compress long sessions…☆13Jul 5, 2026Updated 4 months ago