Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Speculative decoding and prefix caching benchmarked, plus DFlash 2 — the only Qwen3.8-27B build that can serve it under vLLM.
☆56Sep 29, 2026Updated 2 weeks ago
Alternatives and similar repositories for Qwen3.8-27B-FP8-on-a-single-DGX-Spark
Users that are interested in Qwen3.8-27B-FP8-on-a-single-DGX-Spark are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Serving 4-bit Qwen3.8-27B on a single DGX Spark (GB10): 75 tok/s single-stream, 246 tok/s aggregate at 8-way concurrency. NVFP4 vs MixedI…☆51Sep 29, 2026Updated 2 weeks ago
- MiMo-V2.5 NVFP4 4-bit weights + NVFP4 4-bit KV cache + DFlash speculative decoding on 2× NVIDIA DGX Spark — 1M context, 3.4M-token KV poo…☆18Jul 13, 2026Updated 3 months ago
- DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)☆31Aug 3, 2026Updated 2 months ago
- Run DeepSeek-V4-Flash at full 1M context AND two MiniMax H3 video instances on the same two DGX Sparks. Benchmarked C1-C6.☆35Aug 7, 2026Updated 2 months ago
- vLLM deployment for Unsloth Qwen3.6-35B-A3B-NVFP4-Fast on NVIDIA DGX Spark☆70Jul 29, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark☆411Sep 29, 2026Updated 2 weeks ago
- English guide + one-command patcher for the vLLM spin-wait bug that overheats NVIDIA DGX Spark / GB10. Credit: nacyot. CPU cores spin at …☆24Aug 17, 2026Updated 2 months ago
- Self-contained DeepSeek V4 Flash DSpark TP=2 recipe for 2x DGX Spark with 62 tok/s benchmark☆24Jul 13, 2026Updated 3 months ago
- GLM-5.3-Flash NVFP4 on 4x NVIDIA DGX Spark: vLLM TP4, DFlash2 adaptive draft, measured FP8 vs NVFP4 vs EXL3 vs SGLang☆37Sep 29, 2026Updated 2 weeks ago
- Custom inference recipes for NVIDIA DGX Spark — Qwen 122B DFlash hybrid☆81Updated this week
- CUDA Blackwell performance fork of antirez/ds4 (DeepSeek-V4-Flash): ~4x prefill, ~1.5x decode, continuous batching, weight server, DSpark☆77Sep 4, 2026Updated last month
- Strata fork that runs GLM-5.3-Flash (320B-A18B, 157 GB) on one PC: RTX 5090 + 128 GB RAM + NVMe, ~30 tok/s chat. Fork of Niko1221/Strata …☆32Updated this week
- ☆71Oct 10, 2026Updated last week
- Project in Rails using Sencha Touch☆11Sep 1, 2011Updated 15 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Downloadable, self-hosted desktop ERP for business operations. Modular, source-available core, MIT modules, no cloud required.☆30Updated this week
- keys-DGX-Sparkticus Utimate Power Pack Unleashed (Dual DGX-Sparks Needed)☆43Aug 23, 2026Updated last month
- gravity simulation examples using SIMD☆77Aug 15, 2026Updated 2 months ago
- Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE☆151Updated this week
- qwen38-flash-next recipe for tp=2 GB10☆127Oct 6, 2026Updated last week
- Save pages, selections, and images to Memos from Chrome or Firefox, clipped as Markdown with a link to the source.☆41Updated this week
- SeaSearch is a multi-tenant search engine with full-text indexing and vector indexing. Elasticsearch-compatible and S3-backed.☆33Updated this week
- Defender Signature Update Race Condition LPE☆31Apr 9, 2026Updated 6 months ago
- Image to mesh anim with AI☆75Aug 15, 2026Updated 2 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- 尝试复现S1☆15Mar 18, 2025Updated last year
- Browser automation for AI agents in your real, logged-in Chrome. You watch every action and can veto any tab. Chrome extension + zero-dep…☆14Updated this week
- Proves your PostgreSQL and MySQL backups actually restore, before you find out the hard way.☆113Sep 8, 2026Updated last month
- Two-node DGX Spark/ASUS GX10 DeepSeek V4 Flash DSpark NVFP4 port for vLLM 0.25, with live dashboard and reproducible deployment.☆81Sep 13, 2026Updated last month
- High-performance WebAssembly headless spreadsheet engine for web apps☆34Updated this week
- Three.js WebGPU sample scene using speedball-gi (DDGI)☆49Oct 10, 2026Updated last week
- LLM inference in C/C++☆56Aug 8, 2026Updated 2 months ago
- This is a simple application that demonstrates how to have idiomatic layouts that adapt to different device form factors.☆15Jul 25, 2011Updated 15 years ago
- NebulaPulsar is a proof-of-concept in-memory implant framework for Java (JSP) and ASP.NET (ASPX/ASHX/ASMX) webshells, originally develope…☆47Jul 1, 2026Updated 3 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Qwen3.8-Flash-Next (NVFP4) on DGX Spark in vLLM: one Spark 43.9 tok/s with our disk-backed n-gram table patch, staged gather and reduced-…☆128Sep 7, 2026Updated last month
- macOS menubar app that visually rotates or spins another app's window, using ScreenCaptureKit to fake what macOS has no API to do☆49Oct 9, 2026Updated last week
- Automated end-to-end data preprocessing, model training, and evaluation pipeline☆17Jun 3, 2026Updated 4 months ago
- A meta-harness for coding agents to follow proper Software Development Lifecycle practices. Can also write code from specs. Based on li…☆25Updated this week
- 慕课网liuyubobobo的Python3机器学习手打笔记/课件/源码资料。喜欢的点个star，目前还没有更新完，会一直更新。☆14Jul 13, 2020Updated 6 years ago
- Single-request LLM serving recipes, patches, and benchmarks for modified RTX 2080 Ti 22GB / SM75 systems☆92Jun 10, 2026Updated 4 months ago
- Helpful Tools for the Nvidia DGX Spark AI Personal Supercomputer☆31Mar 6, 2026Updated 7 months ago