TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.
☆113Apr 30, 2026Updated 5 months ago
Alternatives and similar repositories for turboquant-mlx
Users that are interested in turboquant-mlx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TurboQuant MLX: Flagship high-performance model quantization for Apple Silicon. Squeeze maximum inference speed and memory efficiency out…☆50Aug 5, 2026Updated 2 months ago
- A tiny server to run local inference on MLX model in the style of OpenAI☆13Jan 31, 2024Updated 2 years ago
- ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache…☆778Updated this week
- GUF to MLX Converter; LM studio advanced tips; Simple text generation using Apple's MLX framework;Enhanced MLX implementation with transf…☆43Updated this week
- 🚀 [Project] Agentis is an application interface for your local AI models with Ollama allowing you to speak with text and voice with your…☆18Jan 23, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- OpenClaw AI Agent Swarm Dashboard☆35Apr 6, 2026Updated 6 months ago
- Rust bindings for Apple's FoundationModels.framework☆24Aug 16, 2026Updated last month
- TurboMLX v0.1 Research Preview public source tree for Qwen3.5-focused MLX TurboQuant experiments.☆121May 16, 2026Updated 4 months ago
- ☆15May 17, 2024Updated 2 years ago
- Micro Kernel wrinting in Swift Embedded for Arch ARM 64☆20Sep 13, 2026Updated 3 weeks ago
- Python toolkit for SIM/eSIM and eUICC work: SCP03, SCP80, SCP11 (relay, local, eIM), SAIP profile packages, and a simulated UICC/eUICC en…☆25Sep 6, 2026Updated last month
- Moshi-Finetune-MLX lets you fine-tune Moshi (Native, Real-Time, Speech-to-Speech) models all on Apple Silicon.☆26Apr 21, 2026Updated 5 months ago
- An on device Agent Runtime☆23May 13, 2026Updated 4 months ago
- MLX Studio - Easiest way to run LLM's on your Mac. All in one engine.☆985Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Pure Rust implementation of Google's TurboQuant (ICLR 2026) — KV cache compression for LLMs☆37Apr 19, 2026Updated 5 months ago
- A customizable Claude Code setup for knowledge workers: agents, safety hooks, skills, memory, and an Obsidian knowledge base. Clone, run …☆33Sep 25, 2026Updated 2 weeks ago
- Anthropic MCP client for macOS☆15Jan 5, 2025Updated last year
- 🧠 Bio-Agent OS: 🇻🇳 Bio-Inspired Memory Framework for AI Agents (OpenClaw/ERP). Researched & Developed by Dev Tuan Anh Ha (Locaith Solu…☆20Aug 20, 2026Updated last month
- Build real software step-by-step with Claude, Codex, OpenCode, Gemini, Cursor, and other agents☆14Mar 29, 2026Updated 6 months ago
- ☆68Jun 4, 2026Updated 4 months ago
- import your conversation history into AI 🫚☆17Sep 7, 2026Updated last month
- JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon☆229Updated this week
- ⚡️ The fastest way to run local LLMs on Apple Silicon — sub-second model loads, beats Ollama on throughput, tail latency, and full-respon…☆20Oct 3, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Run 70B+ LLMs on Apple Silicon by using SSD as extended memory — intelligent layer streaming and caching for Mac☆53Aug 24, 2026Updated last month
- ☆42Mar 12, 2026Updated 6 months ago
- ☆12Aug 1, 2025Updated last year
- REAM: Merging Improves Pruning of Experts in LLMs☆27Apr 16, 2026Updated 5 months ago
- Agentic Runtime Extensible Server. A composable AI agent runtime in Rust based on the Cordis framework☆17Updated this week
- A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI ·…☆64Updated this week
- An Opencode plugin for managing git worktrees.☆77Updated this week
- Classic R.P.S.L.S. created on the Sense-HAT and RaspPi 2☆12May 4, 2020Updated 6 years ago
- A self-hosted AI toolkit running locally via Docker Compose, bundling an LLM gateway, workflow automation, and a chat UI — all backed by …☆16May 17, 2026Updated 4 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆20Apr 14, 2025Updated last year
- ☆199Mar 29, 2026Updated 6 months ago
- High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU…☆17Jul 6, 2026Updated 3 months ago
- Accepts a Hugging Face model URL, automatically downloads and quantizes it using Bits and Bytes.☆38Mar 12, 2024Updated 2 years ago
- ☆16May 25, 2024Updated 2 years ago
- Experimental framework taking inspiration from biological systems, combining compression-based architectures, group theory, and symmetry …☆14Nov 13, 2025Updated 10 months ago
- ☆16Mar 1, 2026Updated 7 months ago