Sealbook
Sealbook / Open source / Agentes de IA y apps con LLM

youssofal/MTPLX

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 model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

anthropic-compatibleapple-siliconclaude-codeflash-nextinference-enginellm-inferencelocal-ailocal-llmmacosmetal
GitHub ↗Sitio ↗

Licencia y mantenimiento

Apache-2.0 es una licencia permisiva: uso comercial libre con atribución.

Último cambio de código hace 10 días.

Proyectos similares

RepositorioEstrellasLenguajeLicenciaActividad
1manaflow-ai/cmuxOpen source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, an★ 28.2kSwiftOtherActivo
2mozilla-ai/llamafileDistribute and run LLMs with a single file.★ 26.4kC++OtherActivo
3jundot/omlxLLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar★ 22.9kPythonApache-2.0Activo
4morluto/reaReverse engineer anything with agents, from app behavior down to native binaries.★ 319.5kTypeScriptMITActivo
5affaan-m/ECCThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code★ 283.1kJavaScriptMITActivo
6NousResearch/hermes-agentThe agent that grows with you★ 254.9kPythonMITActivo
7DietrichGebert/ponytailMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.★ 166.9kJavaScriptMITActivo
8farion1231/cc-switchA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ★ 145.8kRustMITActivo