rockmatrix-ai/EdgeRock
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 13 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
A 4B-parameter multimodal model for text and image reasoning, with constant-size attention history (about 72 MiB per sequence at 256K context) to free GPU memory for sustained reasoning and concurrent serving. Includes inference and evaluation code, plus quantized packages in…
Who it's for
Developers deploying reasoning models on memory-constrained GPUs or serving many concurrent long-context requests
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up rockmatrix-ai/EdgeRock in my project. Follow its README: https://github.com/rockmatrix-ai/EdgeRock. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
18,265 GitHub repos watched and ranked every hour. Figures as of 20 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/rockmatrix-ai/EdgeRock?ref=badge)Similar repos
- Edge0-AI/Edge0
Open-source streaming MoE inference framework that runs large sparse-MoE models on consumer hardware by streaming expert weights from SSD on demand. A trained prerouter predicts expert routing one ste
- 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
- deepseek-ai/DeepInfer
Open-source offline inference framework for DeepSeek models, offering optimized kernels, MoE expert and attention parallelism, speculative decoding, asynchronous scheduling, deterministic sampling and
- MemTensor/MemT-1.0
A research model family, MemT-1.0, that adds trainable native memory blocks alongside transformer attention so models retain historical information across turns without re-reading the original context
- Indras-Mirror/Xolotl
A C++ inference engine and OpenAI/Anthropic-compatible server, forked from Strata, that runs large MoE models such as DeepSeek-V4.1-Flash (552B) on one 24 GB NVIDIA GPU by tiering expert weights acros
- 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