Havuz

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

Pure-Rust MoE inference engine for Qwen3.5/3.6/3.8 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server. 2x llama.cpp

Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion ima

Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and

Local inference for diffusion language models (LLaDA, Dream), written in Mojo

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

Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR,

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cp

Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts

llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s

Bilingual English and Mandarin text to speech in C++ and GGUF. Voice design, cloning, direction and experimental voice conversion. Vulkan ba

A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimiz

Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, ben

Open-source control panel for the real llama.cpp: see where a model lands in your VRAM before loading, every llama-server flag per model, on

CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accu

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE

Screen Translator, Android ekranındaki yazıları OCR ile tanıyıp çeviren ve sonucu ekranın üzerine yerleştiren bir uygulamadır.

Neden yükseliyor · 97 günde 906 yıldız alması, özellikle oyun ve manga çevirisi gibi belirgin bir kullanım alanına hitap ettiğine işaret ediyor. Ancak son 28 günde 2 commit ve 1 farklı yazar bilgisi, ilginin sürdürülebilir geliştirme faaliyetiyle desteklendiğine dair sınırlı kanıt sunuyor.

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine

Local-first AI chat client combining SillyTavern-style character cards, LM Studio-style GGUF model management, Ollama/OpenAI-compatible APIs

Zero-overhead, terminal-native local-LLM orchestrator. Run any engine, any model via the same proxy.

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark,

Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).

Open-source desktop AI agent: built-in free model, local GGUF models via llama.cpp, dispatch tasks from WeChat/Feishu/DingTalk. Files, brows

Open-source voice typing for Windows and macOS — a Wispr Flow / Superwhisper alternative. Press a shortcut, speak, and AI-polished text land

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

Atomic Agent, yerel veya cloud modellerle çalışan ve browser, dosya, onaylı shell komutları ile MCP araçlarını kullanabilen bir AI agent uygulamasıdır.

Neden yükseliyor · 159 günlük bir repoda 2.505 yıldız ve son 28 günde 648 commit dikkat çekiyor; yerel modellerle çalışan kapsamlı bir agent vaadi ve README'deki GAIA L1 karşılaştırması ilgiyi artırmış olabilir. Ancak commitlerin yalnızca 2 farklı yazardan gelmesi aktivitenin geniş bir katkıcı tabanına yayıldığını göstermiyor; yükselişin kesin nedeni bilinmiyor.

User friendly GUI for configuring and launching llama.cpp

The most advanced, fully offline client-side AI suite on Android today.

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf

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

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

AI inference, packed simply. A blazing-fast, zero-dependency WebGPU runtime to run GGUF models directly in the browser. Features a symmetric

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

Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

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