MiaAI-Lab/GLM-5.3-Flash-DGX-Sparks-1104

App

Get alerts like this View on GitHub Website Share on X

Can I trust it?

Worth a closer look before you use it.

Warnings Check
Very new: it was created 3 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

Recipe that serves the GLM-5.3-Flash model from an EXL3 checkpoint across two NVIDIA DGX Sparks at tensor parallel 2, using the TensorFold native Zig/CUDA server built in Docker for sm_121. Includes start and stop scripts, a dry-run mode, and measured throughput and prefill…

Who it's for

Engineers running large language models on two linked NVIDIA DGX Sparks who want a tensor-parallel GLM-5.3-Flash deployment

How to use it

Install

./start.sh

From its README. Check it there before running it.

Ready-made installers, when the project publishes them, are on its latest release.

Downloads (if any)

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up MiaAI-Lab/GLM-5.3-Flash-DGX-Sparks-1104 in my project. Follow its README: https://github.com/MiaAI-Lab/GLM-5.3-Flash-DGX-Sparks-1104. Explain each step and check it is safe before running anything.

Star curve

87From 0 to 87 stars between 4 Nov 2026 and 7 Nov 2026.

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![MiaAI-Lab/GLM-5.3-Flash-DGX-Sparks-1104 on RepoAlerts](https://repoalerts.com/badge/MiaAI-Lab/GLM-5.3-Flash-DGX-Sparks-1104.svg)](https://repoalerts.com/repo/MiaAI-Lab/GLM-5.3-Flash-DGX-Sparks-1104?ref=badge)

Share on X

MiaAI-Lab/DeepSeek-v4.1-Flash-1017-2x-DGX-Sparks
Serves the DeepSeek-V4.1-Flash-1017 model split across two NVIDIA DGX Sparks through an OpenAI-compatible API on port 8888. Uses the TensorFold native Zig engine, a 2.9 bpw EXL3 quantization, a 1,048,
AppModels & inferencePython · 431 stars · +59 this week · 20 days old
mw00/project-maya
Runs GLM-5.3-Flash and DeepSeek-V4.1-Flash-1017 locally on one or more NVIDIA or AMD GPUs, with an engine, server, browser dashboard, quantization tools and OpenAI- and Anthropic-compatible API. Exper
AppModels & inferenceCuda · 2,613 stars · +311 this week · 32 days old
StartLuxLabs/StartLux-Prism
Inference server for StartLux-Decision models on NVIDIA GPUs. It runs the released GGUF files with int8 or 4-bit tensor-core kernels behind a /v1/systemone API, returning a calibrated probability for
CLI toolModels & inferencePython · 330 stars · +141 this week · 25 days old
plotarmordev/drama-tensorfold
Recipe that builds the TensorFold native Zig/CUDA engine with opt-in patches to run Fish Audio's Drama 3 text-to-speech on an NVIDIA GB10. It starts a local server with an OpenAI-style /v1/audio/speec
ResourceModels & inferencePython · 148 stars · +3 this week · 22 days old
flitai-io/gpuworks
A GPU management and model-serving platform that joins bare-metal, cloud and private VM GPU nodes into one cluster, deploys models with engines such as vLLM and SGLang, and exposes them through an Ope
AppDev infrastructureGo · 147 stars · +145 this week · 16 days old · HN 30 pts
NVIDIA/spark-local-inference
A local inference server for NVIDIA SM120/SM121 GPUs aimed at long conversations, coding agents and repeated tool use. Models are prepared at build time with PyTorch, Transformers and FlashInfer, then
AppModels & inferenceRust · 780 stars · +77 this week · 18 days old