Measured speed-ups for MiniMax H3 on one RTX 5090 (ComfyUI): INT8 attention, FastH3 LoRA conversion, distributed segments, and what didn't work
☆32Sep 14, 2026Updated last month
Alternatives and similar repositories for minimax-h3-notes
Users that are interested in minimax-h3-notes are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆19Updated this week
- An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine tha…☆54Updated this week
- ☆19Jul 9, 2026Updated 3 months ago
- Seamless long-form MiniMax H3 video generation for ComfyUI with native AV latent continuity, chunked sampling, session resume, and Spectr…☆203Updated this week
- ☆61Sep 19, 2026Updated 3 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Qwen3.8 27B for DGX Spark / RTX 6000 PRO☆100Aug 14, 2026Updated 2 months ago
- Veda Sparse Attention for ComfyUI☆184Oct 11, 2026Updated last week
- Caesar III on an iPad-shaped canvas, powered by Augustus.☆50Oct 4, 2026Updated 2 weeks ago
- DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.☆126Sep 16, 2026Updated last month
- ☆36Updated this week
- Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins☆529Updated this week
- Native macOS menu bar app — tmux session manager, Keep Awake / closed-lid mode (lid shut, work running), long-running script launcher (OC…☆16Oct 6, 2026Updated last week
- DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM ki…☆68Updated this week
- Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache☆166Sep 3, 2026Updated last month
- 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.
- Real-time talking character on a single RTX 5090 — LTX-2.5 22B + local LLM + TTS, fully local. First video ~2.6s after Enter.☆40Updated this week
- An attempt to reproduce CALM (Continuous Audio Language Models) using DACVAE as the audio VAE.☆19Feb 20, 2026Updated 7 months ago
- An open-source AI hedge fund. A panel of AI analysts and quant models research tickers, each forms a view, and the portfolio layer turns …☆20Jul 27, 2026Updated 2 months ago
- Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins☆1,271Updated this week
- We gave AI models telepathy.☆18Sep 25, 2026Updated 3 weeks ago
- Manga / black & white comic filter for ComfyUI: crisp lines, flat tones, real screentone (halftone), solid blacks and panel frames.☆67Updated this week
- A local-first React demo for chatting with an animated SVG avatar, featuring TTS, lip sync, visual effects, and YouTube Live comment repl…☆32Sep 29, 2026Updated 2 weeks ago
- NeurIPS 2026☆94Updated this week
- TypeScript MCP server for Adobe After Effects (Windows & macOS) — project/comp/layer introspection, atomic undo-grouped operations, JSON …☆121Updated 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.
- 从哥飞的公众号文章中提炼成SEO 教程☆117Sep 30, 2026Updated 2 weeks ago
- ComfyUI custom node for using .char. Exports refmode, lora adapters, guided prompts for your consistent character.☆88Oct 9, 2026Updated last week
- GLM-5.2-Int4-Int8 on 8x GB10 cluster☆39Jul 30, 2026Updated 2 months ago
- touri: open-source desktop app for AI agent bots (Codex, Claude, OpenCode) with isolated VMs, browser and computer use.☆68Updated this week
- ☆82Sep 18, 2026Updated last month
- A powerful, ComfyUI Custom node automation suite for generating cinema-production-grade prompts explicitly formatted for the **MiniMax H3…☆249Sep 12, 2026Updated last month
- Track and extract any 3D object from video. C++/GGML convertion of Meta's sam3d PyTorch model plus a demo app☆54Sep 21, 2026Updated 3 weeks ago
- Claude Code の応答が英語に切り替わったら、日本語で書き直させる Stop hook☆67Updated this week
- Video Delta Net hybrid attention for MiniMax-H3 as a native ComfyUI node.☆241Sep 12, 2026Updated last month
- 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.
- Sol-attn comfy plug-in just for Blackwell☆69Aug 4, 2026Updated 2 months ago
- Official implementation of PRISM: Polynomial Representations for Interaction-Structured Motor Control☆26Updated this week
- Capture App Store screenshots for iOS and macOS apps across every required device size in one command. Supports iPhone, iPad, Apple Watch…☆27Updated this week
- LLM‑driven autoregressive flow matching for unified speech‑music‑sound‑effect audio scene generation☆100Aug 13, 2026Updated 2 months ago
- ChatGPT协议注册机，支持跳过接码并自动导入sub2api☆127Jul 22, 2026Updated 2 months ago
- TypeScript monorepo for the be-music BMS/BMSON toolchain☆15Updated this week
- Metal Cuda Direct Memory Access☆197Updated this week