Run MoE models beyond VRAM on AMD, NVIDIA & Intel GPUs. Vulkan-powered, portable Windows app with automatic setup. | 让游戏显卡跑起超显存大模型，支持 AMD、NVIDIA、Intel，免安装、自动配置。只需13MB，即下即用！
☆353Nov 7, 2026Updated this week
Alternatives and similar repositories for MoE4All
Users that are interested in MoE4All are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Qwen3.8-27B via vLLM on a single AMD Radeon AI PRO R9700 (gfx1201, 32 GiB) — bare, script-free setup guide, written to be executed by an …☆13Sep 3, 2026Updated 2 months ago
- KVMem virtualizes KV memory across inference backends to make ultra-long-context local AI accessible on limited hardware.☆1,278Updated this week
- ☆60Sep 4, 2026Updated 2 months ago
- ☆11Oct 18, 2026Updated 3 weeks ago
- 为哔哩哔哩提供恰饭片段自动跳过功能的 Xposed 模块☆19Oct 30, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 200+ tok/s single-reques…☆1,207Oct 1, 2026Updated last month
- One process = one agent. Go single-repo personal agent runtime with decoupled plugins.☆34Updated this week
- ☆103Updated this week
- RDNA-native LLM inference engine in Rust.☆804Updated this week
- High-performance single-GPU inference for selected model checkpoints and GPUs.☆3,283Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆18Sep 11, 2026Updated last month
- NInfer-KVMem-Async☆10Updated this week
- Reed 一苇 — 一苇以航，轻渡学海。独立 Windows 学习 Agent，支持角色技能、记忆与 Obsidian 笔记库。☆17Oct 24, 2026Updated 2 weeks ago
- Working on the fastest vllm path for AMD Radeon AI PRO R9700☆107Updated this week
- 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.
- AI Agent Engine/Harness/TUI with Zero Dependencies☆25Jul 30, 2026Updated 3 months ago
- ☆19Oct 29, 2026Updated last week
- Mac mini 最强本地推理引擎 - 融合 oMLX、ThunderLLAMA、ClawGate 的优势，配备 Web 管理面板和 macOS 菜单栏应用☆14Mar 24, 2026Updated 7 months ago
- GPU Unlock — NVIDIA SM speed-select override kernel module. Merges gpu-unlock-ada (AD102/AD103) and gpu-unlock (GA10x + resume). Docs: ht…☆33Oct 27, 2026Updated last week
- Claude Opus 4.7/8 破甲工具。利用系统提示原文 default_stance 漏洞——「edgy/hypothetical/playful 请求不构成拒绝理由」——将自己的规则反制成豁免通行证。一键自动发现 Claude Code 路径并部署 CLAUDE.…☆21Jul 6, 2026Updated 4 months ago
- ComfyUI 图库插件——在 ComfyUI 侧边栏内嵌一个「图库」tab，用于浏览、管理、检索本地 ComfyUI 产出图片，支持AI反推、翻译、评分、解析工作流☆19Oct 16, 2026Updated 3 weeks ago
- Bonsai-27B x NInfer local deployment project (RTX 5080, ternary quantization)☆51Oct 6, 2026Updated last month
- 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- …☆2,632Updated this week
- Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop ker…☆33Aug 29, 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.
- Windows desktop control panel for local llama.cpp server☆393Jul 13, 2026Updated 3 months ago
- One line of NInfer for the Blackwell, Ada Lovelace, Ampere, Turing and Volta NVIDIA GPUs, consolidated from the forks that carry it: GGUF…☆201Updated this week
- Linux driver for wireless adapters with Realtek rtl8811au/rtl8812au/rtl8821au chipsets☆12Apr 29, 2020Updated 6 years ago
- DeepSeek Harness桌面端，采用绝对纯净原则，基于tauri实现☆34Oct 30, 2026Updated last week
- Mage-VL-4B 多模态模型 Web Demo☆33Aug 1, 2026Updated 3 months ago
- $0.047/s or ¥0.3/s seedance2 low price☆26Sep 22, 2026Updated last month
- Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~4…☆479Updated this week
- vLLM optimized for AMD☆28Updated this week
- Phone-free bridge connecting the Enabot EBO SE robot to Home Assistant — no phone, no cloud. Runs the TUTK/Kalay client on a Raspberry Pi…☆16Jun 20, 2026Updated 4 months 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.
- ☆411Sep 18, 2026Updated last month
- ☆34Updated this week
- AMD + OptiScaler DLSS 5/6X & XeFG 30X Multi-Frame Generation integration, configurations and deployment guides. …☆147Updated this week
- Codeberg fork of StillDeadcode / vllm-radiance which is a custom vllm tuned for R9700 GPU's☆160Oct 18, 2026Updated 2 weeks ago
- Desktop UI for the NInfer local LLM inference engine☆33Updated this week
- ☆18Aug 31, 2026Updated 2 months ago
- An extension utility for llama.cpp, used with 3090*2 + Strix Halo. llama.cpp的拓展小工具，自用于3090*2 + Strix Halo。☆418Updated this week