Kindi 0.6: fast local LLM inference on low-cost GPUs and CPUs. DeepSeek-V4.1-Flash (552B) at 18.7 tok/s on one RTX 3060 12 GB with a dual-Xeon DDR4 server. Ternary Bonsai 2B-27B, AH-Nanbeige4.3-33B, Nemotron 3.5 Lightning 30B-A3B. NVIDIA from the Quadro K420 to the RTX 50 series, AMD Radeon graphics, Windows and Linux. OpenAI-compatible server.
☆172Nov 13, 2026Updated this week
Alternatives and similar repositories for kindi
Users that are interested in kindi are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- llama.cpp fork for two V100 32GB cards to run Qwen3.8FlashNext☆14Nov 3, 2026Updated last week
- Strata for a PC with two NVIDIA GPUs and 32 GB of RAM: the low-RAM mode on a layer split, both cards working at the same time. 143 tok/s …☆85Oct 6, 2026Updated last month
- Self-hostable runtime for persistent autonomous coding agents — KVM-isolated VMs (or rootless containers), A2A-protocol executor with sig…☆14Sep 5, 2026Updated 2 months ago
- Lightweight Rust reimplementation of OpenClaw — self-hosted AI assistant, <10MB idle RAM, WASM sandboxed tools☆14Mar 1, 2026Updated 8 months ago
- Strata minus the bullshit. clone, rsync to prod, compile and go☆237Nov 6, 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.
- 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…☆189Updated this week
- Open source cooling solution for the **AMD Radeon Instinct MI50** (Vega 20).☆18May 29, 2026Updated 5 months ago
- 两张 V100 跑 Qwen3.8-27B 到 100 tok/s(186K 上下文):重写 sm70 注意力内核 + 多卡张量并行。Fork of geoffwatts/ninfer-v100.☆21Sep 28, 2026Updated last month
- Configurable AI chat with TTS/STT☆281Updated this week
- Demo: HTML pages from a coding agent at markdown token cost. A component kit, a Claude Code skill, and the 72-run benchmark behind it.☆51Oct 13, 2026Updated last month
- porkchop port for cbd and c5☆19Jul 1, 2026Updated 4 months ago
- LLM inference in C/C++☆150Oct 16, 2026Updated 3 weeks ago
- ⚡ Accelerate chat and IDE workflows with a proxy for llama.cpp, managing slots and cached context for efficient, low-latency interactions…☆10Oct 14, 2026Updated last month
- CUDA engine that splits every layer of a production quality MoE LLM across three PCIe V100 cards delivering 382 tok/s on a used $1,800 bo…☆82Nov 7, 2026Updated last 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.
- ☆13Jun 26, 2023Updated 3 years ago
- Desktop UI for the NInfer local LLM inference engine☆33Nov 2, 2026Updated 2 weeks ago
- Work satellites with your IC-705 and iPhone☆11Aug 25, 2024Updated 2 years ago
- 2080ti TU102 doing the unlock trick☆150Oct 22, 2026Updated 3 weeks ago
- GA100 voltage glitch resources☆225Updated this week
- Way of the Samurai 2 (PS2) — native Linux decompilation port☆20Oct 16, 2026Updated last month
- A Public Template For Building A Docker MCP GUI App With Remote and Local Servers Using Docker MCP Gateway and Model Runner☆27Jan 16, 2026Updated 9 months ago
- Fast fork of llama.cpp designed for Qwen3.8-Flash-Next☆431Updated this week
- [COLM 2025] Official repo for Self-Steering Language Models☆30Aug 8, 2025Updated last year
- 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.
- Builds per arch baseline images for MiGraphX with ORT and PyTorch☆12Oct 6, 2026Updated last month
- Frozen Soldat HTML Game☆23Updated this week
- Disciplined AI coding mode. Understand deeply, write minimally, never hallucinate, stay consistent. Based on Ponytail & LLM Wiki.☆17Nov 4, 2026Updated last week
- ☆26Oct 3, 2026Updated last month
- Resources for I Want My EIP, presented at Derbycon 2017☆11Sep 23, 2017Updated 9 years ago
- An improved Rolling template for Unreal Engine 5.6 and higher☆17Sep 9, 2026Updated 2 months ago
- ☆15May 30, 2026Updated 5 months ago
- Project remakes main features of video game Powerslide☆10Aug 20, 2026Updated 2 months ago
- Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar tool calls 9/9. Same ternar…☆100Updated 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.
- An official code repository for SEMamba++ (Interspeech 2026, Long track).☆18Oct 26, 2026Updated 3 weeks ago
- Local voice dictation for talking to coding agents. No subscription or word limit. Windows packages and Linux source.☆16Oct 13, 2026Updated last month
- A C++ game engine for 2D and pixel art games, with destructible voxel worlds, an integrated editor, and JavaScript gameplay scripting.☆21Oct 19, 2026Updated 3 weeks ago
- llama.cpp patch: faster MoE offload for models that don't fit in VRAM☆70Updated this week
- Fork of Android 16 Terminal with dependency on AVF removed☆14Dec 9, 2025Updated 11 months ago
- ☆65Oct 26, 2026Updated 3 weeks ago
- ☆16Oct 8, 2025Updated last year
Are these results useful?