synchopate/llama-modchip
Public🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.
Find trending repositories by name or description.
🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.
Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.
Open-source Windows game resource manager. Suppresses background processes, gives games exclusive CPU cores, steers device interrupts off game cores, applies per-game GPU driver, memory and power policies, and restores every change after play. No injection, no telemetry. GPL-3.0.
An open-source IDE for C# and .NET, built with Avalonia, for Windows, macOS and Linux: a Roslyn-powered editor, its own debugger with Hot Reload, a CPU and memory profiler, XAML tooling for Avalonia and WPF, and an MCP server for coding agents.
AirSnip 轻截:1 MB 的 Windows 截图标注工具(Rust,纯 CPU 渲染,待机 0% CPU)
Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt
Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU/GPU inference.
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
Community Windows startup animation launcher for Codex with live-window handoff and reversible shortcut integration
Converts decrypted PS5 game dumps into native Windows executables via binary relinking, replacement system libraries, and Vulkan. No CPU emulation.
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
Turn your cameras into Home Assistant sensors with a local AI: garage door open/closed, people and cars, water, gas and power meters read by any camera or ESP32-CAM. 100% local, any CPU.
An AI editor that watches its own cut: talking-head / AI-avatar video → auto-edited short video. 网感口播精剪:数字人/真人口播 → AI 自动精剪成网感动效短视频 → 可选剪映分层草稿
One command downloads a complete offline, no-internet emergency library: local AI (CPU/GPU), document Q&A, full Wikipedia, offline maps for any country/region (default US), survival/repair/medical archives, and public-domain manuals. Asks only where to save.
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
wayland terminal based on libghostty. cpu rendered, like foot
Sampling CPU and HEAP profiler for Java featuring AsyncGetCallTrace + perf_events
早耳 - Real-time multilingual speech-to-text on CPU only. Live subtitles, browser dashboard, speaker labels, translation. No GPU, no cloud.
Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.
Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parallel architecture, suitable for MOE model hybrid inference.
Linux运维监控工具,支持系统硬件信息,内存,CPU,温度,磁盘空间及IO,硬盘smart,GPU,防火墙,网络流量速率等监控,服务接口监测,大屏展示,拓扑图,端口监控,进程监控,docker监控,日志监控,文件防篡改,数据库监控,指令批量下发执行,web ssh,Linux面板(探针),告警,SNMP监测,K8S,Redis,Nginx,Kafka,资产管理,计划任务,密码管理,工作笔记
:green_book: Example tmux configuration - screen + vim key-bindings, system stat, cpu load bar.
Free cross-platform educational MIPS64 CPU Simulator. Experimental web version: https://web.edumips.org.
Recursive version of fs.readdir with small RAM & CPU footprint.
PerfView is a CPU and memory performance-analysis tool
PicoRV32 - A Size-Optimized RISC-V CPU
⚡️⚡️⚡️Blazing fast correlation functions on the CPU.
cmix is a lossless data compression program aimed at optimizing compression ratio at the cost of high CPU/memory usage.
Command-line cross-compiler of assembly language for Z80 CPU.
Sampling CPU profiler for Ruby