Havuz

DeepSeek V4 Flash 284B on AMD Strix Halo (gfx1151) — up to 32 tok/s decode & ~250 tok/s prefill via ROCmFPX, DSpark & ROCm 7.2

Unified native AI runtime for Java 17+, Java 22+ (Panama FFM), Android & C++. Run GGUF LLMs, Vision, Video, Whisper ASR, TTS & Embeddings in

Native runtime, integrations, and reproducible packaging for BTL-3 and BTL-3 Compact

Native macOS app for local AI image generation and editing on Apple silicon: Z-Image Turbo, Qwen-Image-2.1, Krea 2 Turbo, Anima Turbo and MO

Deploy Qwen3.6-35B-A3B (Q4_K_XL) + MTP speculative decoding on a single NVIDIA L4 24GB — GCP g2-standard-8 — via the official llama.cpp Dock

Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Custom CPU, ROCm, Vulkan, CUDA, Metal and Level Zero

A 6.87 GiB GGUF build of Qwen 3.8 27B — full 27B quality on 8 GB RAM. 96.7% HumanEval, 92.9% MMLU retention, no distillation.

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

Use any AI model, locally or in the cloud, while tracking on-device token usage and collecting token telemetry data.

Look inside any local LLM (GGUF from Ollama, LM Studio, Hugging Face, Jan, llama.cpp): layers, heads, vocabulary, chat template, weights. Ex

RenderCaption - Offline AI Speech to Text & Subtitles Generator.

Local AI model manager

Private, offline AI assistant for Android and Windows: run local LLMs (Gemma 4, Qwen, any GGUF) on your phone or PC with llama.cpp, CUDA and

High performance inference engine

🔥 Run large open language models on your phone. A C++20 GGUF inference engine that streams models larger than RAM from flash, paces itself b

Run local LLMs entirely in your browser, with no server, no install and no traces. A private, single-file AI chat UI and AGENT that also wor

Benchmark llama.cpp on your own GPU/CPU boxes and compare against everyone else's — sweep runner, an sha256-keyed index of ~4M GGUF files, a

Run stock llama.cpp with the stock Unsloth Qwen3.6-35B-A3B 4-bit on a 16 GB Mac.

Portable offline AI assistant powered by llama.cpp and GGUF models. Run a private local chatbot directly from a USB drive on Windows with no

A local music generation and remix studio built on audio.cpp. Generate, repaint, split into stems and swap voices, with every take kept and

Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, ll

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

Speech-first inference runtime in Rust — TTS / ASR / speech-to-speech / VC / speaker ID / VAD. An ONNX Runtime alternative that loads GGUF &

ComfyUI deployment kit for Qwen-Image-2.1 Uncensored (GGUF): ready-to-use t2i & image-edit workflows, ComfyUI-GGUF architecture patches, and

MoE expert compression toolkit — prune, merge, and forge specialist models for local inference.

Local, offline text-to-speech and voice cloning on audio.cpp — multi-voice narration, voice design, sound/music generation, and a real-time

Run open AI models on your own computer — a friendly desktop app and local gateway for llama.cpp and more. Private, free, open source.

Zero-G Reverse Engineering Anything & Verified Safe Rust Reconstruction for Gemini 4 Argon + Google Antigravity 2.0 (4-Mount Recon Kits, Who

Ternary decision scoring with Jevfire-style inference, typed APIs, and reproducible Persian evaluation.

Evidence-backed structural validation of Kimi K3 UD-IQ1_M and UD-Q4_K_XL split GGUF releases using OMIV.

Typed decisions from unstructured state: one forward pass, zero generated text. Local, deterministic, Jev-compatible. Not affiliated with ty

Measures which GGUF quant of a model to run on your GPU: real speed and quality loss (KL divergence), not estimates.

Published: 2026-10-18

High-performance, high-precision, locally-fast-deployed Jev-class medical decision service on national medical exams — four readings, one ro

Published: 2026-10-19

Published: 2026-10-18