Havuz

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine f

Bonsai-demo, Bonsai 2 27B modelini yerel donanımda çalıştırmak için kurulum betikleri ve llama.cpp/MLX tabanlı demo arayüzleri sunar.

Neden yükseliyor · Yerel LLM çalıştırma ve düşük bitli model formatlarına ilgiyle örtüşüyor; 186 günde 3.148 yıldızın yanında son 28 günde 54 commit ve 25 farklı yazar, depoda kayda değer güncel aktivite olduğunu gösteriyor. Bu metrikler ilginin nedenini tek başına kanıtlamaz; artışın kaynağına dair veri verilmemiş.

Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.

Spark-X2.5, yerel çalıştırma ve agent iş akışları için tasarlanmış 1.7B ve 4B boyutlarında açık dil modelleri serisidir.

Neden yükseliyor · Yeni model serisi; uzun context, küçük model boyutu ve agent/coding yeteneklerini aynı anda öne çıkarıyor. README'de 34 günlük yaş, 386 yıldız ve son 28 günde 9 commit ile 2 farklı yazar bilgisi var; bunlar erken ilgi ve güncel çalışma gösteriyor, ancak model performansını bağımsız olarak kanıtlamıyor.

Slotstream, büyük bir MoE modelini SSD’den parça parça yükleyip yoğun kullanılan expert’leri bellekte önbelleğe alarak Apple Silicon Mac’lerde çalıştıran yerel bir inference engine’dir.

Neden yükseliyor · README, 48 GB M5 Pro üzerinde belirli koşullarda 15.86 tok/s ölçümü ve prompt işleme iyileştirmeleri yayımlıyor; son 28 günde 271 commit ve 5 farklı yazar da yoğun geliştirme faaliyetine işaret ediyor. Ancak proje yalnızca 30 günlük ve mevcut sürüm için nitelikli tam yanıt hızı ölçümünün hâlâ beklediği belirtiliyor.

Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https

SiliconScope, Apple Silicon Mac’lerde sistem kaynaklarını ve özel hızlandırıcıları izleyen, ayrıca uzaktaki makineleri aynı panele ekleyebilen bir macOS monitörüdür.

Neden yükseliyor · 111 günde 966 yıldıza ulaşması ve son 28 günde 48 commit alması dikkat çekiyor; README’deki ANE ve memory-bandwidth ölçümleriyle uzaktaki makineleri tek panelde toplama özellikleri de ayırt edici bir kullanım vaadi sunuyor. Üç farklı yazar aktiviteye işaret etse de ekip genişliği sınırlı; yıldızlar tek başına benimseme veya kalite kanıtı değil.

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-awa

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache co

Governed neural weight editing and coding model adaptation. Native Rust patches, exact rollback, LoRA, Claude Code routing, and reproducible

A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more

LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint on

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven

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.

Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.

A local-first workspace for documents, tasks and meetings on macOS — nested spaces, typed properties, relations and saved views, with transc

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud,

Your free book and audiobook laboratory. Turn the PDFs you own into chapter-marked M4B audiobooks, read-along books and bilingual editions,

LLM frontend for roleplay and creative writing

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU

Open, calibrated, single-pass typed-decision models (4B & 27B) for finance and trading

train your own chatbot from scratch on a mac

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

A local LLM server built for concurrent work. Drop-in replacement for Ollama and/or OpenAI and Ollama APIs on one port. Requests that share

Run Kimi K3 (2.8 T parameters,1.56 TB) on iPhone 16 Pro? Weights stream from your SSD through a memory budget you set. Free, local, on Mac a

A realtime assistant for Mac and Windows. Talk to it and it answers aloud, shows your schedule and mail as cards, and hands longer work to a

A 4B decision model built for Korean.

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-

Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.

An educational macOS app: build and chat with a tiny language model, trained on your Mac

Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwrig

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI

TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.

Free, open-source AI autocomplete for macOS — on-device ghost-text suggestions in every app. A private, local Cotypist alternative built wit

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

Run and serve local models headlessly

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

Extreme weight + KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant)

Ultra-Sparse Adaptation of 1-Bit LLMs via XOR Patches

Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, te

System-wide, on-device AI autocomplete for macOS — Copilot-style suggestions in every text field, fully offline and private.

Macaw — on-device AI agent for macOS. 2.7B LFM2.5 fine-tune, MLX 4-bit, 97 macOS tools, no cloud.