Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
☆1,224Nov 18, 2026Updated this week
Alternatives and similar repositories for inferssd
Users that are interested in inferssd are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Device-native foundation models: 145B on a laptop, 35B on a phone. Latent MoE, SSD-streamed weights, a router that predicts loads a step …☆12,008Updated this week
- ☆3,554Oct 20, 2026Updated 3 weeks ago
- Token-scale scientific discovery engine — autonomous hypothesis generation, experiment execution, and knowledge graph synthesis☆3,100Oct 24, 2026Updated 3 weeks ago
- Monid - OpenRouter for agent tools. Join our community at https://discord.gg/rQzztcgJV8☆6,211Updated this week
- Everything your Hermes Bots and tools are waiting on you for, in one list: stuck sessions, failed crons, benched keys, PRs, and cards Bot…☆13Oct 23, 2026Updated 3 weeks 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.
- Run thousands of AI agent sandboxes on the cheapest machines.☆6,095Updated this week
- Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Man…☆4,320Nov 12, 2026Updated last week
- See what Claude Code and Codex actually send to the API — and what each part costs.☆5,800Nov 12, 2026Updated last week
- DSHDesktop:DeepSeek Harness Desktop / DeepSeek Harness 桌面版☆19,586Updated this week
- 🦍 Memorilla: Latent Semantic Memory for LLMs☆1,471Updated this week
- 一张照片生成 AI 数字人口播:本地 ComfyUI 全流程(Qwen3-TTS 克隆声音 + MiniMax H3 对口型 + Qwen Image + Music 3),不花积分;5 种剪辑风格 + 48 个博主级包装组件。AI digital-human talkin…☆36Updated this week
- Open source personal agent with its own computer. It chases invoices, preps your calls and cancels trials on real websites, and asks befo…☆2,454Updated this week
- While guanacos are slightly taller than llamas (measuring up to 6.2 feet from head to toe), they are generally slimmer and weigh less. Gu…☆13Oct 20, 2026Updated 3 weeks ago
- PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-the…☆191Nov 9, 2026Updated last 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.
- Semantic SQL for Postgres, powered by Jev☆15Sep 19, 2026Updated 2 months ago
- ☆3,054Sep 17, 2026Updated 2 months ago
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆45,204Updated this week
- ☆112Nov 2, 2026Updated 2 weeks ago
- A design system for AI applications. Material, physical, tactile, technical.☆2,353Oct 31, 2026Updated 2 weeks ago
- MicroCUDA is a lightweight framework that brings GPU‑like compute abstractions and a local AI agent to your CPU☆17Jul 22, 2026Updated 3 months ago
- FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.☆17,289Updated this week
- Enhancing Handwritten Quranic Arabic Recognition through Deep Learning☆21Jan 23, 2026Updated 9 months ago
- Run 50-280 GB MoE LLMs (DeepSeek V4/V4.1 Flash, GLM-5.3-Flash, Qwen3.8-Flash-Next, Ornith) on one consumer GPU: experts spread over VRAM,…☆40Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Qwen3.5-2B with a filesystem compiled and inserted directly into its weights.☆97Nov 4, 2026Updated 2 weeks ago
- Jito-MEV Bundle☆27Nov 7, 2026Updated last week
- Open-source Google Business Profile manager: reviews, posts, profile edits, rank tracking and keyword research for every location, with a…☆20Updated this week
- WCXB: Web Content Extraction Benchmark — 2,008 pages, 7 page types, 1,613 domains. The largest open benchmark for web content extraction,…☆15Apr 4, 2026Updated 7 months ago
- llama.cpp fork for two V100 32GB cards to run Qwen3.8FlashNext☆15Nov 3, 2026Updated 2 weeks ago
- A minimalist and powerful harness with one tool: a persistent Python REPL.☆321Updated this week
- Android messenger with a full Parano1d node, encrypted chats and native NOID payments. Internet, app-only VPN and Bluetooth.☆31Updated this week
- Correctness-first EVM interpreter in Bend targeting Amsterdam. Working interpreter; full conformance and proofs in progress.☆21Sep 18, 2026Updated 2 months ago
- Standalone NVIDIA RTX Video Super Resolution CLI - GPU decode -> VSR -> encode in one pass, no ComfyUI☆23Sep 9, 2026Updated 2 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.
- ARTEX - AI autonomous penetration testing system (English translation; upstream: Autumn-27/ARTEX, AGPL-3.0)☆8,269Updated this week
- A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from…☆51,788Updated this week
- Memory efficient and high performance Mixture-of-Experts inference for Apple Silicon☆126Updated this week
- A curated list of awesome platforms, tools, practices and resources that helps run LLMs locally☆17Mar 30, 2026Updated 7 months ago
- MAPLE: Manifold-Activated Pruning of Latent Experts for Sub-2-BPW MoE LLMs☆62Updated this week
- ☆126Nov 2, 2026Updated 2 weeks ago
- Official Voyager desktop downloads and update feed☆22Updated this week
Are these results useful?