Havuz

On-device simultaneous interpretation on Apple Silicon — VoxCPM2 on MLX at the core, streaming TTS in ~170 ms, voice clone, any-pair transla

OnDevice Local AI Studio — run LLMs on iPhone offline. SwiftUI workbench with MLX, llama.cpp, whisper.cpp, RAG, and authenticated OpenAI/Ant

DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-

方寸智匣 LocalBrain：本地大模型、文件与媒体工作台。Windows/Linux 2.2.9，Apple Silicon Mac 2.2.9；按平台维护运行环境，支持本地工具与 MCP 接入。

Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text gene

Offline LLM app for iPhone: run open models from Hugging Face on-device with llama.cpp, MLX, Core ML and Apple Foundation Models. No account

Tiny engine, immense models — run large MoE LLMs (gpt-oss, Mixtral, Qwen3-MoE) on ordinary machines by streaming experts from disk. OpenAI-c

A 4B decision model built for Korean.

Distil an expensive LLM API call on a narrow task into a small local model: capture traffic, curate, LoRA fine-tune with MLX on Apple Silico

Apple Silicon 本地视觉语言模型 CLI：用 MLX/Qwen3-VL 描述图片、图像问答与提示词反推。Offline vision-language CLI for image understanding, visual Q&A and reverse prompt

On-device meeting capture, dictation, and vault-native knowledge layer for macOS. Nothing leaves your Mac.

Your AI intranet: network the computers you already own for inference and training.

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and

Writing that's kin to yours

Run NVIDIA's tri-modal Nemotron Omni (text+vision+audio) entirely on Apple Silicon — pure MLX runtime, parity-verified against NVIDIA's refe

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from