Qwen3.8-27B on one DGX Spark GB10: DFlash 2 for 65 tok/s C1 and 120 C4; EAGLE 3/1/4 for ~191 C8, ~330 C16 and ~535 C32; native 262K, pinned SGLang.
☆13Oct 6, 2026Updated 2 weeks ago
Alternatives and similar repositories for qwen3.8-27b-kearuga-sglang-dgx-spark-dflash2
Users that are interested in qwen3.8-27b-kearuga-sglang-dgx-spark-dflash2 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 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. Spe…☆55Sep 29, 2026Updated 3 weeks ago
- Qwen3.8-27B on one DGX Spark: SGLang + DFlash2 recipe, engine image, benchmarks, data and charts. By @redp314☆37Sep 6, 2026Updated last month
- Serve DeepSeek-V4-Flash-Vision EXL3 MixedK (full 256 experts) on one NVIDIA DGX Spark with vLLM — recipe, loader patches, and receipts☆14Sep 7, 2026Updated last month
- Serve typed-decision (System 1) models — Laya or your own — on NVIDIA GPUs or Apple Silicon, with a Jev-compatible API and coding-agent i…☆35Sep 24, 2026Updated last month
- 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 3 weeks ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Verified Qwen3.8 Flash-Next GGUF recipe for one NVIDIA DGX Spark or ASUS Ascent GX10☆61Updated this week
- Run Qwen3.8-Flash-Next (180B) on a single DGX Spark by keeping its 51B n-gram embedding table on NVMe☆125Aug 30, 2026Updated last month
- A community-owned map of LLM inference engine configurations — benchmarks, evals and coverage gaps, hosted on GitHub Pages. The repo is t…☆16Updated this week
- An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine tha…☆58Updated this week
- DeepSeek v4 Flash EXL3 on one DGX Spark☆349Aug 24, 2026Updated 2 months ago
- Getting Qwen's Qwen4-architecture preview (Qwen3.8-Flash-Next) to run on a single DGX Spark GB10 — 125.9 GiB of weights against 117 GiB o…☆21Oct 14, 2026Updated last week
- An update to the old simple-calc☆10Dec 22, 2025Updated 10 months ago
- GLM-5.3-Flash EXL3 K2 2.33bpw on ONE DGX Spark: native MTP (layer 45, 288 experts), CUDA graphs on, full 262,144 ctx. Measured ~19 tok/s …☆12Sep 19, 2026Updated last month
- A native vLLM 0.26 DGX Spark recipe for Qwen3.6 35B-A3B NVFP4, focused on high aggregate throughput, 262K context, and production-friendl…☆15Aug 31, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Run one local MLX model across Apple Silicon Macs on macOS and on Omarchy Linux, served as one OpenAI-compatible endpoint☆23Updated this week
- ☆14Jan 29, 2026Updated 8 months ago
- ☆53Sep 13, 2026Updated last month
- Cake Build addin for managing (simctl) Apple iOS/watchOS/appleTV simulators☆15Dec 8, 2022Updated 3 years ago
- Tough Fuzzer is an obstacle course for go-fuzz composed of a series of small code samples which encapsulate the most common obstacles to …☆19Sep 26, 2021Updated 5 years ago
- My website☆13Jun 24, 2026Updated 4 months ago
- Documentation for the iMETRO robot facility.☆24Apr 6, 2026Updated 6 months ago
- Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090☆25Sep 20, 2026Updated last month
- Blazor, ASP.NET Core, Xamarin, .NET Standard <3☆14Dec 8, 2022Updated 3 years ago
- 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.
- Coding stack built completely on local models☆21Aug 22, 2026Updated 2 months ago
- Qwen3.8-Flash-Next on one DGX Spark: tuned vLLM launch, context sweep, tuning ladder. By @redp314☆21Sep 21, 2026Updated last month
- Pyranid is a zero-dependency JDBC interface for modern Java applications.☆20Oct 14, 2026Updated last week
- DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.☆126Sep 16, 2026Updated last month
- Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)☆615Oct 4, 2026Updated 3 weeks ago
- Metal Cuda Direct Memory Access☆201Oct 15, 2026Updated last week
- Projects to explore detailed outbreak paths. Mostly dataviz using Power BI☆14Oct 19, 2024Updated 2 years ago
- Hey Muse. A fork of TECHO5 that turns an Echo Show 5 into the voice of Muse, Meta's AI agent: a "Hey Muse" wake word on the device, pairi…☆25Oct 7, 2026Updated 2 weeks ago
- Weakness-Oriented Assertion Recommendation For Golang (source code for submission in ISSRE'19)☆23Jan 7, 2020Updated 6 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆16May 24, 2026Updated 5 months ago
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆12Oct 13, 2026Updated last week
- Turn the Hacker News front page into local AI art. Powered by mlx-vlm, MFlux, and Apple Silicon.☆35Aug 3, 2026Updated 2 months ago
- Agentic-coding oriented inference engine for N x V100-SXM2, based on SGLang: GLM-5.3-Flash, Qwen3.8-Flash-Next, DeepSeek-V4.1-Flash, Mini…☆33Oct 7, 2026Updated 2 weeks ago
- Reproducible Qwen3.8-27B NVFP4 + DFlash2 recipe and qualification evidence for one NVIDIA DGX Spark☆30Aug 21, 2026Updated 2 months ago
- This Project aims to port/build well known and commonly used data structures to GO.☆28Apr 2, 2022Updated 4 years ago
- Docker Compose plugin for Apple's container CLI with Homebrew tap.☆37Updated this week