Turbo1Bit: Combining 1-bit LLM weights (Bonsai) with TurboQuant KV cache compression for maximum inference efficiency. 4.2x KV cache compression + 16x weight compression = ~10x total memory reduction.
☆31Apr 2, 2026Updated 7 months ago
Alternatives and similar repositories for Turbo1bit
Users that are interested in Turbo1bit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with PrismML Q1_0_G128 1-bit quant support, RotorQuant, TurboQuant, EAGLE3 and P-EAGLE sp…☆26Jun 23, 2026Updated 4 months ago
- A general-purpose LLM harness and coding agent implemented as a single, hackable Bash script.☆12Oct 21, 2026Updated last week
- A simple no-install web UI for Ollama and OAI-Compatible APIs!☆31Jan 30, 2025Updated last year
- ☆24Oct 7, 2026Updated 3 weeks ago
- 1bit llama.cpp gguf weights paired with turboquant 4 bit kv cache☆24Apr 4, 2026Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- TurboQuant 3-bit KV-cache quantization for llama.cpp☆54Jul 30, 2026Updated 3 months ago
- Decentralizing distribution of open-source AI models.☆24Updated this week
- Dice Language Support for VS Code☆10Sep 29, 2020Updated 6 years ago
- A lightweight web browser chatbot interface for Ollama models☆25Apr 6, 2025Updated last year
- A fast, polished, local Web UI for llama-server, vLLM, and OpenAI-compatible APIs — with charts, diagrams, and MCP tools.☆32Oct 26, 2026Updated last week
- A simple library to better manage AI prompts in your Rust code.☆14Apr 29, 2024Updated 2 years ago
- A text to audio pipeline using Riffusion (a finetuned stablediffusion model) and using RAVE a audio to audio AutoEncoder.☆17Jun 27, 2025Updated last year
- An understandable fast brainfuck interpreter using closures rather than bytecode☆13Apr 16, 2025Updated last year
- An example project to demonstrate https://github.com/rvantonder/hack-parallel☆13May 18, 2020Updated 6 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Test your local LLMs on the AIME problems☆39Jun 7, 2025Updated last year
- ChatGPT over SMS using Twilio Programmable Messaging, OpenAI API, Flask☆13Jan 22, 2023Updated 3 years ago
- Creating AI agents with the simplicity of Python in Java.☆14Mar 21, 2026Updated 7 months ago
- you can add in your own data in .jsonl file!☆12Jun 14, 2023Updated 3 years ago
- Headless terminal emulator CLI powered by libghostty-vt☆19Apr 8, 2026Updated 6 months ago
- Dashboard v5 Coming Soon!!☆65Feb 15, 2026Updated 8 months ago
- LLVM JIT Cycle Accurate Simulator for HardCaml☆13May 21, 2017Updated 9 years ago
- ☆17May 29, 2026Updated 5 months ago
- numpy ufuncs for vector similarity☆13Nov 26, 2023Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A tiny nearest-neighbor embedding database written in C☆19Feb 18, 2026Updated 8 months ago
- Open-source reference implementation of the Thermodynamic Cognition Index (TCI) — surplus metric for persistent ML agents☆17Jun 18, 2026Updated 4 months ago
- 🐾 Complete REST API for ClawHub skills marketplace data☆17Apr 6, 2026Updated 6 months ago
- KoboldCpp Smart Launcher with GPU Layer and Tensor Override Tuning☆29May 18, 2025Updated last year
- A virtual machine for the Epiphany processor architecture on Parallella boards.☆11Nov 28, 2013Updated 12 years ago
- Official source code for the paper "Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents"☆13Oct 3, 2026Updated last month
- Real-World Security Conversations for AI Training☆11Jul 6, 2026Updated 3 months ago
- ☆10Mar 28, 2024Updated 2 years ago
- One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.☆16Aug 5, 2026Updated 2 months ago
- 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.
- Flan T5 LLM fine-tuning, by attaching a regression model last hidden layers activations. Runs on colab with A100 40gb☆13Mar 24, 2023Updated 3 years ago
- ☆11Dec 4, 2011Updated 14 years ago
- Local First AI Operating System with Longterm Memory, MultiAgent Orchestration, Persona Switching and more.☆14Updated this week
- ELF-parsing library written in OCaml for OCaml☆14May 30, 2012Updated 14 years ago
- Composer Package and Git Repository Mirror via Satis☆13Oct 7, 2021Updated 5 years ago
- Profile-guided GPU kernel optimizer for AMD/RDNA3. Auto-tunes llama.cpp MMVQ kernels per model shape. 2x decode speedup on 7900 XTX.☆70Sep 5, 2026Updated last month
- Payer-side AI-assisted prior authorization review using Microsoft Agent Framework with four Foundry Hosted Agents (Compliance, Clinical, …☆20Aug 11, 2026Updated 2 months ago