Giant MoE models on a single consumer GPU by streaming experts from SSD. CUDA fork of antirez/ds4: runs GLM-5.2 (743B), Tencent Hy3 (295B), and DeepSeek 4 Flash, with io_uring expert streaming, LFU host cache, cross-layer expert prefetch, and the first MTP speculative decoding for GLM-5.2.
☆40Jul 12, 2026Updated 3 months ago
Alternatives and similar repositories for neutronstar
Users that are interested in neutronstar are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 多智能体协同、自动化管线沙盒与商业验证试验仓 / Multi-agent sandbox and execution validation chamber☆58Sep 25, 2026Updated 3 weeks ago
- SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB G…☆230Sep 1, 2026Updated last month
- cyberneurova-DeepSeek-V4-Flash-abliterated-aligned local inference engine with M5 Metal support☆36Sep 12, 2026Updated last month
- Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents☆41Updated this week
- MCP server + OpenAI-compatible shim to use Meta Muse (muse.ai, Hatch) by driving the real logged-in Chrome.☆56Sep 30, 2026Updated 2 weeks ago
- 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.
- Portable C++17 implementation of YuE2 AI Music Generator using GGML. Text + lyrics in, stereo 48kHz MP3 or WAV out. Runs on CPU, CUDA, RO…☆43Updated this week
- an MCP for querying the EVM☆12Apr 1, 2025Updated last year
- High performance cross-platform immediate-mode GUI rendering library.☆47Updated this week
- Vision & image analysis skill for Claude Code & Codex. 帮不能看图的模型看懂图片和视频。☆161Sep 10, 2026Updated last month
- TikTok marketing skills for Claude Code and Codex: 3-second video hooks, captions, trend mapping, and a weekly plan. Draft, humanize, and…☆77Updated this week
- A minimal MiniCPM5-1B model inference engine built purely in Rust☆42Aug 14, 2026Updated 2 months ago
- Open-source Fugu: the open-source LLM orchestration brain.☆67Jul 4, 2026Updated 3 months ago
- Local Grok tools as MCP for ChatGPT Web. No model.☆46Sep 4, 2026Updated last month
- Run Hy3 on a 10GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦☆71Aug 3, 2026Updated 2 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- A zig library to manipulate gemini text files☆16Oct 4, 2024Updated 2 years ago
- MCP server that gives AI agents a real Chrome: Google/Bing search and JavaScript-rendered page fetches over CDP (Linux/macOS).☆68Updated this week
- The setup I use for pi. Changes a ton, don't recommend hard copying it, just a taste of what's possible with it☆181Updated this week
- DeepSeek Harness plugin for Android — build, run, and interact with a live emulator or USB device stream inside a conversation, driven en…☆187Oct 8, 2026Updated last week
- A template for Zig projects☆15Apr 17, 2026Updated 6 months ago
- A portable multi-system Sega emulator for Genesis, Sega CD, Master System, Game Gear, and SG-1000 🎮☆35Updated this week
- RedisGraph Julia client☆12Oct 29, 2025Updated 11 months ago
- MCP server for Software Defined Radio — control RTL-SDR & HackRF from Claude/LLM. ADS-B aircraft tracking, AIS ship tracking, POCSAG page…☆29Jul 21, 2026Updated 2 months ago
- Positional embeddings for enriching sequence data with positional information☆10Nov 24, 2025Updated 10 months ago
- 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.
- Capminal Smart Contracts Repository☆96Sep 6, 2026Updated last month
- Custom MCP [Connector] for AI chat web [Claude|ChatGPT|Grok...] use Files/Shell on your computer directly☆143Oct 11, 2026Updated last week
- ☆14Sep 8, 2025Updated last year
- Desktop GUI for the omp coding agent: parallel sessions, visual tool calls, model/provider management, and usage analytics.☆77Updated this week
- Qwen3.8-Flash-Next (125B MoE) on a 8GB+ Multi Vendor GPU 🥳No CUDA！☆210Updated this week
- Turn ChatGPT web into a local coding agent via MCP — read/write files, run shell, git, apply_patch. Works with Developer Mode + OpenAI Se…☆104Sep 30, 2026Updated 2 weeks ago
- A 49M-parameter Kimi K3-inspired language model trainable on one 8GB GPU☆96Jul 28, 2026Updated 2 months ago
- ☆15Feb 10, 2026Updated 8 months ago
- ☆19Updated this 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.
- Run autonomous AI agents across machines using a distributed filesystem.☆17Apr 3, 2026Updated 6 months ago
- ☆18Jun 17, 2025Updated last year
- ☆14Apr 16, 2025Updated last year
- ☆15May 8, 2025Updated last year
- Capminal Agent Skills☆31Aug 9, 2026Updated 2 months ago
- Qwen-CUA: Native Computer Use for (Almost) Everything — a screenshot-driven agent that operates computers with keyboard and mouse, jointl…☆223Aug 26, 2026Updated last month
- 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 3 months ago