mtp

OpenMTP - Advanced Android File Transfer Application for macOS

The fastest way to run Qwen 3.8 Flash Next and Qwen 3.8 27B on a Mac: 125 tok/s in OpenCode on an M5 Max. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

Android File Transfer for Linux (and macOS!)

MTProxyTLS一键安装绿色脚本

This repository holds the source code of Microsoft.Testing.Platform (MTP), a lightweight alternative to VSTest, as well as MSTest adapter and framework.

A modern Android File Transfer tool for macOS with AI supercharged.

llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% throughput).

Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)

Lightweight USB Media Transfer Protocol (MTP) responder daemon for GNU/Linux

Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.

A library to access MTP (Media Transfer Protocol) Devices.

MTProxy(MTPROTO) v2 One-Click Installation

PoC exploit for arbitrary file read/write in locked Samsung Android device via MTP (SVE-2017-10086)

Open recipes, engine patches, and benchmark harnesses for LLM inference on Intel Arc Pro B60/B70 (Battlemage, Xe2). MoE 35B at 160 t/s decode / 7.5K t/s prefill single-stream, 27B at 50~ t/s decode / 1.7K t/s prefill single stream. vLLM XPU MTP unlocked. Muse Glimmer recipe added!!

llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): TurboQuant KV cache, MTP speculative decoding with a 64K draft-vocabulary shortlist, custom SM86 + Qwen kernels. 90 tok/s over a 100K-token generation at temperature 1.

Qwen4-Exp (Qwen3.8-Flash-Next) SWA + MTP + PLE-on-iswa — bounded deep-context decode w/ long-range recall, TBQ4 4.25 bpv KV, DSpark + RotorQuant. Main (master) = Qwen4-Exp build; the Qwen35 SWA hybrid lives on the qwen35 branch. RTX 4090.

Qwen3.8-Flash-Next on 2× RTX 3090 + 128 GB RAM. Experimental peaks: 1,860 tok/s prefill at 260K input; 89.1 tok/s decode at 128K input. Full 256K context.

NeveAI é uma plataforma de IA local privacy-first, desenvolvida para oferecer uma experiência de alta performance na execução de LLMs, reduzindo a dependência de grandes plataformas, assinaturas caras e APIs externas e servindo como uma alternativa offline, privada e independente.

Sync files through USB over rsync

Python library used to communicate with PTP devices like Parrot Sequoia