Unofficial M1/M2 port of Inco's Splash (upstream is M3+ only): Metal kernels written for Apple7/8 GPUs, prebuilt releases.
☆212Nov 6, 2026Updated this week
Alternatives and similar repositories for splash
Users that are interested in splash are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A local inference engine for Apple silicon, built around the model.☆2,110Updated this week
- Empirical benchmarks and quality evaluations of Qwen3.8-27B with Multi-Token Prediction (MTP) across Splash, MTPLX, MLX, and llama.cpp on…☆21Sep 21, 2026Updated last month
- ☆38Oct 22, 2026Updated 2 weeks ago
- DS Menu Bar - A Lightweight Menu Bar Control for DwarfStar Server (ds4-server)☆18Updated this week
- HIP kernels for AMD Strix Halo (gfx1151) and a vLLM plugin that runs them on stock upstream vLLM: up to 31x faster prefill and ~2x decode…☆21Updated 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.
- The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B…☆2,673Updated this week
- embeddable llm agent in c with lua plugins☆13Updated this week
- works well with rocks; native Apple Silicon inference engine for capable and tiny models (ternary, Qwen) via MLX Swift. Hadamard-rotated …☆29Sep 26, 2026Updated last month
- Provides a Container executing TWS/Gateway in an isolated environment.☆10Feb 13, 2023Updated 3 years ago
- Run large AI models fast on low RAM Mac's using SSD/NVM streaming.☆64Updated this week
- lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.☆335Oct 21, 2026Updated 2 weeks ago
- Real-time vLLM + TensorFold performance dashboard TUI — single file, zero dependencies☆13Oct 19, 2026Updated 2 weeks ago
- Qwen3.8-27B-GSQ3 on one RTX 4080: 100k context with rk4v4-e8, up to 2720 tok/s prefill and 262 tok/s generation☆34Oct 9, 2026Updated 3 weeks ago
- The MCP gateway platform. PlexMCP gives you a unified gateway to manage, orchestrate, and secure your MCP servers.☆13Jan 9, 2026Updated 9 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar☆23,416Updated this week
- Python Version of Infinitesimal Plane-based Pose Estimation (IPPE)☆10Jun 17, 2026Updated 4 months ago
- Live, on-device transcription of any app on your Mac, with speaker names.☆13Updated this week
- Fast, lightweight and stealth Firecrawl alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Fir…☆79Oct 18, 2026Updated 2 weeks ago
- ☆12Mar 24, 2018Updated 8 years ago
- A parents-only web admin for a self-hosted kids' phone line☆31Oct 22, 2026Updated 2 weeks ago
- A durable, project-wide thought queue for Pi sessions.☆15Oct 19, 2026Updated 2 weeks ago
- rkllm rust ffi binding☆13Oct 19, 2026Updated 2 weeks ago
- Rust LLM inference engine tuned for AMD Strix Halo (gfx1151): a fork of Strata with ggml/llama.cpp-derived HIP kernels. Five models on on…☆38Updated 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.
- Claude Desktop for Debian-based Linux distributions☆12Oct 31, 2025Updated last year
- GLM-5.3-Flash EXL3 K2 2.33bpw on ONE DGX Spark: native MTP (layer 45, 288 experts), CUDA graphs on, full 262,144 ctx. Measured ~19 tok/s …☆11Sep 19, 2026Updated last month
- VecoLuc is a scalable vector search engine that leverages Apache Lucene and the JDK's incubator vector API for high-performance vector op…☆11Aug 22, 2024Updated 2 years ago
- A lightweight macOS app for LLM API proxying — automatic format translation (Anthropic ↔ OpenAI), parameter injection, model mapping, and…☆10Jul 24, 2026Updated 3 months ago
- A Rust-native LLM serving engine. One binary, no Python runtime.☆22Updated this week
- Postman for your MCP server with a Claude chat that calls your tools☆14Jun 3, 2025Updated last year
- A Simple node.js-base terminal slide tool☆15Sep 27, 2016Updated 10 years ago
- Toolkit for optimizing or building inference engines tailored to your hardware and desired LLM.☆43Updated this week
- Slack for AI Agents☆22Mar 6, 2026Updated 8 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and h…☆288Updated this week
- Docker image with Chrome Remote Desktop☆16Aug 4, 2025Updated last year
- ☆11Jul 6, 2026Updated 4 months ago
- ☆16Sep 29, 2026Updated last month
- A remote control for the pi coding agent. Windows-native, zero third parties.☆10Oct 23, 2026Updated 2 weeks ago
- ☆12Jul 10, 2020Updated 6 years ago
- Fast fork of llama.cpp designed for Qwen3.8-Flash-Next☆306Updated this week