DeepSeek-V4.1-Flash on two NVIDIA DGX Sparks: EXL3 weights from the official checkpoint, upstream vLLM with our patches and decode kernels
☆38Oct 12, 2026Updated this week
Alternatives and similar repositories for dgx-spark-deepseek-v41
Users that are interested in dgx-spark-deepseek-v41 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.☆60Updated this week
- DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM ki…☆68Updated this week
- GLM-5.3 (full) on 3-6 DGX Sparks (GB10): a from-scratch CUDA inference engine☆37Updated this week
- One script to install, run, update, and maintain ComfyUI on the NVIDIA DGX Spark (GB10 Grace Blackwell).☆76Oct 10, 2026Updated last week
- 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
- 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.
- GLM-5.3-Flash (NVFP4) on 2x NVIDIA DGX Spark - vLLM TP2, 262K context, MTP. World-first deploy recipe: 7 day-0 bugs found and fixed, patc…☆236Sep 30, 2026Updated 2 weeks ago
- comfyui optimizations for the dgx spark☆38Apr 30, 2026Updated 5 months ago
- One command turns a DGX Spark or ASUS Ascent GX10 into a private AI server: seven measured, pinned AI lanes (text up to 1M tokens, images…☆229Updated this week
- DeepSeek-V4.1-Flash on 3-4x NVIDIA DGX Sparks☆247Updated this week
- Serve EXL3 (ExLlamaV3 trellis) quantized models on vLLM fork runtimes — any architecture, mixed per-layer bitrates, composable with sourc…☆26Updated this week
- Web UI for sparkrun — launch and monitor inference workloads on NVIDIA DGX Spark☆28Jun 16, 2026Updated 4 months ago
- DeepSeek-V4.1-Flash (552B MoE, MXFP4 experts, 1M ctx) on four NVIDIA DGX Sparks with vLLM TP4: Engram-on-disk patch, sm121 kernel build, …☆110Updated this week
- SearchJev: a fast and calibrated System-1 model for search agents (training code)☆32Oct 4, 2026Updated 2 weeks ago
- qwen38-flash-next recipe for tp=2 GB10☆127Oct 6, 2026Updated last 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.
- Talks for the Impeccable project.☆45Jul 1, 2026Updated 3 months ago
- Dock for Omarchy — clean, modern, high-performance application dock with zero-CPU autohide, tiling window adaptation, and deep customizat…☆46Updated this week
- Parses, validates, hashes, and serializes Nix derivations and constructs their store paths in pure Rust☆26Oct 3, 2026Updated 2 weeks ago
- A Google Colab that runs Elixir livebook w/ BumbleeBee and CUDA acceleration☆10Dec 26, 2022Updated 3 years ago
- ☆28Sep 3, 2026Updated last month
- Community-tested recipes, diagnostics, and benchmarks for CMP 170HX AI workloads☆84Oct 10, 2026Updated last week
- Solana's unofficial Elixir SPL interface☆15Mar 23, 2022Updated 4 years ago
- Remove recognizable AI writing patterns without flattening the writer's voice.☆73Oct 5, 2026Updated last week
- Code, datasets, and results for "The Embedder's Dilemma: LLMs Are Better, but at What Cost?" (COLM 2026). MTEB(LLM) benchmarks 10 LLMs an…☆40Sep 19, 2026Updated 3 weeks 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.
- Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants…☆165Updated this week
- GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe☆108Updated this week
- Skim pages, files, and lists with Jev: keep only what helps with your goal. Saves agent tokens. Built with go/cobra.☆30Updated this week
- Code and report for the project of the MIT course 16.32 Principles of Optimal Control and Estimation☆11Jan 2, 2021Updated 5 years ago
- The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas…☆75Oct 1, 2026Updated 2 weeks ago
- An GB10-optimized inference engine☆108Updated this week
- A script to launch Qwen3.8-Flash-Next in a single DGX-Spark (or its variants) at 40+ tok/s inference speed.☆34Aug 31, 2026Updated last month
- GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold☆457Updated this week
- Byte-safe encoding, decoding, hashing, and restoration for Nix archive formats in pure Rust.☆25Sep 17, 2026Updated last month
- 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.
- Examples using MLX Swift☆13Apr 9, 2025Updated last year
- Wireless headphones in the Omarchy bar — per-earbud battery and noise control☆21Updated this week
- Unofficial PoC: a BERT-style encoder decision engine behind a typed-decision (noul / choice / score) HTTP API. Not affiliated with TypeSa…☆35Sep 22, 2026Updated 3 weeks ago
- Research prototype: run AnyPS5-relinked PS5 titles on iPad via Madeira (Wine ARM64EC + FEX) with MoltenVK☆43Oct 11, 2026Updated last week
- An agent skill with multiple gates to check and to remove any AI slop. Use it with codex/claude code or any of your favorite AI tools.☆95Sep 14, 2026Updated last month
- Recipe for the fastest 4bit qwen3.8FlashNext☆63Oct 6, 2026Updated last week
- Metal Cuda Direct Memory Access☆197Updated this week