NVIDIA/flare-local-inference
App
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created yesterday. 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
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 served by a Rust runtime (Helios) without Python, with CUDA graphs captured…
Who it's for
Developers running local LLM inference on NVIDIA SM120/SM121 workstations or DGX Spark systems, especially for coding agents
How to use it
Ready-made installers, when the project publishes them, are on its latest release.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up NVIDIA/flare-local-inference in my project. Follow its README: https://github.com/NVIDIA/flare-local-inference. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #44, on 21 Oct 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.
18,557 GitHub repos watched and ranked every hour. Figures as of 21 October 2026.
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.
[](https://repoalerts.com/repo/NVIDIA/flare-local-inference?ref=badge)Similar repos
- Indras-Mirror/Xolotl
Local inference engine for large MoE and dense LLMs (DeepSeek-V4.1-Flash, GLM-5.3-Flash, Qwen3.8 models) on a single NVIDIA GPU, with expert weights tiered across VRAM, pinned RAM and NVMe. Serves Ope
- prabanta-dev/janas
A C inference engine for running large mixture-of-experts language models on ordinary computers, with or without a GPU. Weights stay on disk, and the experts each token needs are streamed from an NVMe
- VecSzn/PolyStrata
Runs large open-weight language models locally on a PC with NVIDIA GPUs, using a PolyStrata engine for several models and the Strata engine for Qwen3.8-Flash-Next. Offers OpenAI- and Anthropic-compati
- Lore-Hex/token-exchange-neocloud-in-a-box
Open-source toolkit for running a small confidential GPU inference server: a model runs inside an Intel TDX confidential VM with NVIDIA GPUs in confidential-computing mode, exposed through an OpenAI-c
- mw00/project-maya
A C++ engine, server and dashboard for running the GLM-5.3-Flash and DeepSeek-V4.1-Flash models locally on one to sixteen NVIDIA or AMD GPUs, on Linux or Windows. It offers OpenAI- and Anthropic-compa
- apple-aiml-research/ml-rsi-inference-bench
A long-horizon benchmark for coding agents that improve the inference stack of large language models in vLLM or SGLang. Tasks cover supporting a model on day 0, optimizing it after launch, and repairi