Multi-GPU (tensor-parallel) CUDA megakernel for Qwen3.8-27B GGUF (Q4_K_M, Q5_K_M, Q6_K, Q8_0) with on-device MTP speculative decoding. Fork of open-jet's single-GPU megakernel, extended to 2 GPUs over P2P.
☆16Oct 23, 2026Updated 3 weeks ago
Alternatives and similar repositories for geezuz-qwen3.8-27b-dual-gpu
Users that are interested in geezuz-qwen3.8-27b-dual-gpu are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qw…☆147Updated this week
- Tool schemas get re-prefilled on every LLM request. ContextCache compiles them into a KV cache once, stores it on disk and reuses it acro…☆22Sep 16, 2026Updated 2 months ago
- Qwen3.8-27B EXL3 + DFlash2 speculative decoding on an AMD RX 7900 XTX (exllamav3-rocm): recipe, patches, benchmarks☆23Nov 2, 2026Updated 2 weeks ago
- XiaoZhi ESP32 firmware with Ada UI, power management, and OpenClaw gateway integration for SenseCAP Watcher☆10May 13, 2026Updated 6 months ago
- A .NET library & CLI tool to control NordVPN☆11Dec 29, 2025Updated 10 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.
- Deterministic PyGhidra extraction, triage, and local LLM compiler-backend pipeline for C reimplementation.☆11Oct 18, 2026Updated last month
- OwlLayer AI - Open-source TypeScript Agentic UI SDK for AI-powered interfaces across React, Vue, Angular, Svelte, Vanilla JS/HTML and PHP…☆18Oct 11, 2026Updated last month
- LLM Systems Manager — real-time observability and control for LLM systems☆12Updated this week
- Galahad by Corbenic☆65Nov 4, 2026Updated 2 weeks ago
- OpenAI-compatible proxy that makes local LLMs serving easy and reliable. Sits between your client and any OpenAI-compatible backend, add…☆14Nov 12, 2026Updated last week
- DeepSeek-V4.1-Flash (1017) on one 16 GB GPU + 64 GB RAM, experts streamed from NVMe: llama.cpp patches, a weight assembler, benchmarks an…☆14Nov 9, 2026Updated last week
- ☆12Mar 10, 2022Updated 4 years ago
- Independent Windows/Linux desktop client for Oh My Pi — projects, sessions, native PTY terminals, and provider controls.☆14Updated this week
- AI Optimized Markdown Kanban Board☆16Sep 9, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Three MiniMax H3 ComfyUI workflows for 8GB laptop GPUs (20 / 8 / 4 steps). Includes the model list, launch flags, prompt-structure pitfal…☆25Oct 24, 2026Updated 3 weeks ago
- 🟢 A modern desktop workspace for Claude Code. Open source.☆11Jul 31, 2026Updated 3 months ago
- ☆13Nov 4, 2026Updated 2 weeks ago
- Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,86…☆146Oct 15, 2026Updated last month
- An Autodesk Fusion Add-In for "3d Parametric Splines"☆12Jan 23, 2026Updated 9 months ago
- Unofficial M5StickC Plus S3 (ESP32-S3) port of anthropics/claude-desktop-buddy — BLE bridge firmware that shows Claude Code / Claude Cowo…☆15Apr 18, 2026Updated 7 months ago
- Debian Images for Bobcat 300 Miner☆12Jun 30, 2025Updated last year
- ☆14Jul 24, 2026Updated 3 months ago
- ☆17Jul 17, 2026Updated 4 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results☆19Oct 3, 2026Updated last month
- Local desktop coding assistant you can run with any local model. No API key required. It can read your project, edit files, run commands,…☆19Updated this week
- Fetch only relevant tools for the current conversation and save cost while increasing the precision of your LLM Response☆17Sep 9, 2025Updated last year
- Raspberry Pi Pico Relay Board is developed by SB Components with the potential to control up to 4 appliances and loads up to 240V AC@ 7A,…☆13Mar 26, 2024Updated 2 years ago
- ☆11May 16, 2012Updated 14 years ago
- High-performance universal media optimizer for images, video, and audio. Built with Nuitka and Go, with auto-GPU acceleration and crash-s…☆21Sep 13, 2026Updated 2 months ago
- Library of AI Agent Personas☆14Aug 12, 2025Updated last year
- A bash script that runs local LLMs on Linux with llama.cpp, vLLM or Ollama. It plans GPU memory, checks models for security, benchmarks, …☆18Nov 11, 2026Updated last week
- Ruby library to get the ranking of a url based on a keyword in Bing, Yahoo or Google☆10Aug 19, 2010Updated 16 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A FastAPI application that integrates with Telegram using webhooks and OpenAI Agents SDK for AI-powered stock trading assistance, utilizi…☆17May 11, 2025Updated last year
- Persistent memory for Claude Code, Claude Desktop, and Codex — save once, recall across sessions, shared across all your AI CLIs.☆17Oct 22, 2026Updated 3 weeks ago
- Truthful local registry and event stream for running coding agents☆12Nov 7, 2026Updated last week
- Set or toggle multiple monitor's input sources via DDC/CI☆13Mar 1, 2019Updated 7 years ago
- The chef's standard for AI agent work: twelve rules, a critique gate, and project memory. One skill. Craftsman's taste. Zero AI slop.☆21Aug 26, 2026Updated 2 months ago
- Zero-Node, Zero-Electron DeepSeek Harness distribution powered by Bun, Elysia, and Tauri v2☆13Updated this week
- Pico Cube is a 4x4x4 LED cube HAT for Raspberry Pi Pico with 5V DC operating voltage. Pico cube, a monochromatic( Red, Blue, Green) LED w…☆15Jan 19, 2023Updated 3 years ago
Are these results useful?