dgx-spark repositories

Trending repositories tagged dgx-spark, ranked by trending score. Updated daily.

  1. 1
    Keys-Wasserman/Imagination-Studio-by-keys-Wasserman

    Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slate workflow by Sam Wasserman), render Qwen-Image-2.1 / FLUX3-K pictures and MiniMax H3 / FastH3 video with sound on TensorFold.

    GitHub · Python · 1,208 stars · 223 forks · +26 stars in 24 hours · Trending score 3.38

  2. 2
    Picom-code/pico-dgx-ds4

    DeepSeek V4.1 Flash on 4x DGX Spark: 90/144 tok/s chat/code single-user, 376 tok/s at 16 distinct users, 1M context, images. Fork of blaesus/dsgx10.

    GitHub · Cuda · 150 stars · 28 forks · +28 stars in 24 hours · Trending score 2.78

  3. 3
    bertholomus/deepseek-v4.1-tensorfold-tp2-2xgb10

    BertholomusAI recipe: DeepSeek-V4.1-Flash-1017 on 2x NVIDIA DGX Spark (GB10), our own TensorFold TP2 engine. Weights: bertholomus EXL3 2.5bpw quant (MIT). v0.7.5.

    GitHub · Python · 73 stars · 7 forks · +33 stars in 24 hours · Trending score 2.64

  4. 4
    Deen-Media/dgx-monarch

    Distributed image and video generation in ComfyUI for two NVIDIA DGX Sparks.

    GitHub · Python · 58 stars · 6 forks · +26 stars in 24 hours · Trending score 2.49

  5. 5
    AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash

    Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

    GitHub · Python · 500 stars · 57 forks · +27 stars in 24 hours · Trending score 2.44

  6. 6
    christopherowen/spark-ds41f

    Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a switchless three-node or four-node DGX Spark fabric.

    GitHub · Python · 243 stars · 59 forks · +6 stars in 24 hours · Trending score 2.07

  7. 7
    christopherowen/dgx-spark-networking

    Switchless RoCE collectives, NCCL profiles and fabric tooling for DGX Spark inference recipes

    GitHub · Python · 44 stars · 4 forks · +14 stars in 24 hours · Trending score 1.91

  8. 8
    TandemLLM/TandemEngine

    TandemEngine: local inference that drafts and verifies its own tokens, behind an OpenAI-compatible API.

    GitHub · Python · 82 stars · 17 forks · +8 stars in 24 hours · Trending score 1.72

  9. 9
    hasso5703/alzeo

    Alzeo is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Acer), into a private AI server in one command: measured model lanes, OpenAI and Anthropic APIs, and a local cockpit.

    GitHub · Python · 271 stars · 24 forks · +6 stars in 24 hours · Trending score 1.60

  10. 10
    mARTin-B78/dgx-spark-faster-qwen3-tts

    Run Faster-Qwen3-TTS on NVIDIA DGX Spark GB10 (ARM64/SM121/CUDA13) - OpenAI-compatible TTS API with CUDA graph acceleration

    GitHub · Python · 30 stars · 2 forks · +5 stars in 24 hours · Trending score 1.18

  11. 11
    bertholomus/glm-5.3-exlr8-4x-spark

    GLM-5.3 (full) EXLR8 on four DGX Sparks with gr8: bit275 (~2.75 bpw) manifest, concurrency dial CONC 1/2/4/8, busy guard (BUSY=1, v2), optional SSD KV store and spark-attic

    GitHub · Shell · 12 stars · 0 forks · +2 stars in 24 hours · Trending score 0.93

  12. 12
    bertholomus/spark-attic

    More memory for CUDA on an NVIDIA GB10 (DGX Spark, ASUS Ascent GX10): lend the unused display carveout to vLLM, SGLang and TensorFold as KV cache

    GitHub · Python · 34 stars · 1 forks · 0 stars in 24 hours · Trending score 0.85

  13. 13
    alexellis/switchless-nccl

    Build, load, and verify NCCL for switchless DGX Spark RoCE cycles

    GitHub · Shell · 21 stars · 4 forks · +2 stars in 24 hours · Trending score 0.82

  14. 14
    avifenesh/memra

    Memra is a Rust + CUDA LLM inference engine with hand-written kernels, NVFP4 and mixed-precision execution, and correctness gates scoped to each model and GPU

    GitHub · Rust · 7 stars · 1 forks · +1 stars in 24 hours · Trending score 0.63

  15. 15
    kindlingai/gr8

    A from-scratch CUDA inference engine for 1-6 DGX Sparks (GB10): GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash

    GitHub · Cuda · 83 stars · 16 forks · 0 stars in 24 hours · Trending score 0.61

  16. 16
    FengZhenfei/carrel

    Ontology-Augmented Generation for AI agents.

    GitHub · Python · 808 stars · 18 forks · 0 stars in 24 hours · Trending score 0.59

  17. 17
    atakann/dgx-spark-recipes

    Measured recipes for the NVIDIA DGX Spark, on one or two Sparks: LLM serving, image, video and speech

    GitHub · Python · 19 stars · 0 forks · 0 stars in 24 hours · Trending score 0.55

  18. 18
    timothystewart6/vllm-gb10

    Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on every release.

    GitHub · Python · 61 stars · 7 forks · 0 stars in 24 hours · Trending score 0.47

  19. 19
    bertholomus/beam-1.0-2x-dgx-spark

    Reflection Beam-1.0-501B-A23B (Apache-2.0) on two DGX Spark / GB10: EXL3 3-bit, TP2 with DFlash2 on TensorFold (868K context) or vLLM (655K)

    GitHub · Shell · 9 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46

  20. 20
    CoconutMacaroon/blender-arm64

    Blender for ARM64 Linux with CUDA/OptiX/Vulkan support

    GitHub · Shell · 45 stars · 5 forks · 0 stars in 24 hours · Trending score 0.46

  21. 21
    chadhurley25075-png/pd-bridge

    Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE

    GitHub · Python · 151 stars · 13 forks · +1 stars in 24 hours · Trending score 0.45

  22. 22
    joeynyc/spark-doctor

    Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker issues, and validates vLLM/Ollama/llama.cpp/SGLang recipes.

    GitHub · Python · 166 stars · 15 forks · 0 stars in 24 hours · Trending score 0.40

  23. 23
    Picom-code/pico-dgx-qwen38

    Qwen3.8-Flash-Next on one DGX Spark, official NVIDIA FP4 weights, exact output: 54 chat / 88 code tok/s, 66.9 on 320 held prompts, 288 tok/s at 16 users. TensorFold + MiaAI-Lab recipe + 29 patches.

    GitHub · Python · 16 stars · 0 forks · +1 stars in 24 hours · Trending score 0.38

  24. 24
    Enntity/sparkglm

    Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.

    GitHub · Python · 76 stars · 3 forks · 0 stars in 24 hours · Trending score 0.36