Qwen-Image 2.1 on TensorFold's NVFP4 kernels: a drop-in ComfyUI loader, 4x faster than the GGUF path on one RTX 5070 Ti (native Windows). Work in progress.
☆12Oct 3, 2026Updated 2 weeks ago
Alternatives and similar repositories for qwen-image21-tensorfold-rtx
Users that are interested in qwen-image21-tensorfold-rtx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Native Qt desktop app for building MiniMax H3 reference packages with ComfyUI☆10Oct 8, 2026Updated 2 weeks ago
- GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threa…☆117Updated this week
- ☆20Updated this week
- Windows desktop app that runs data jobs on your own machine with DuckDB and Polars, then publishes the results as Delta tables straight t…☆43Updated this week
- GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold☆481Updated 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.
- Measured speed-ups for MiniMax H3 on one RTX 5090 (ComfyUI): INT8 attention, FastH3 LoRA conversion, distributed segments, and what didn'…☆32Sep 14, 2026Updated last month
- Training-free tweaks for MiniMax H3 in ComfyUI: crisper or smoother skin, a sub-seed style scene re-roll, and a prompt-strength dial for …☆31Sep 25, 2026Updated 3 weeks ago
- Native Tencent Prism video/audio nodes for ComfyUI, with standalone INT8 ConvRot models and complete canvas workflows.☆17Oct 7, 2026Updated 2 weeks ago
- A Claude Code skill that coaches a non-technical person through building their own agentic OS, one layer at a time. Substrate first, mode…☆19Jun 28, 2026Updated 3 months ago
- Official implementation of "Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction".☆36Oct 12, 2026Updated last week
- 高尚姿势编辑器：ComfyUI 1–9 人独立摆姿、9 图输入、彩色编号、站位与转身控制，适配 Qwen Image 2.1。☆21Sep 29, 2026Updated 3 weeks ago
- Fast, capable GLM-5.3-Flash FP4-Local on two DGX Sparks: opinionated Atlas serving and reproducible inference research.☆67Updated this week
- Headless / multi-user serving-mode for the DGX Spark: free unified memory for vLLM by paring back the desktop. Companion to qwen3.5-122B-…☆19Jun 29, 2026Updated 3 months ago
- A compiler-driven simulator for M5Stack StopWatch (C152) firmware: the production C++ runs on your Mac with the device's own font metrics…☆29Aug 20, 2026Updated 2 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.
- ☆12Nov 22, 2025Updated 11 months ago
- 在 dsh 网页中编辑 ComfyUI、实时预览并让 AI 操作工作流。☆20Updated this week
- Powerful standalone ComfyUI custom nodes for managing multiple LoRAs in a single, dynamic interface☆15Aug 4, 2025Updated last year
- vLLM Tune consolidates MoE and FP8 dense GEMM kernel tuning into a single command☆32May 24, 2026Updated 4 months ago
- Official implementation of "GRACE: Generation-Aware Latent Compression for Efficient Video Generation" (arXiv 2610.10524)☆28Oct 12, 2026Updated last week
- The official ImageKit Video Player SDK. Drop-in HTML/JS player built on Video.js with adaptive streaming, AI subtitles, auto-generated ch…☆62Updated this 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…☆84Updated this week
- DeepSeek V4 Flash DSpark DGX Spark TP4 Ring 生产调优与算子工程归档 (LuZ0.4.5)☆17Sep 11, 2026Updated last month
- Pixel-perfect editing for Qwen-Image-Edit-2511 in ComfyUI☆20Jul 9, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- DeepSeek-V4.1-Flash on 4x DGX Spark TP4 switchless RoCE ring - SGLang production recipe, 600K context, DSpark MTP, benchmark archive☆29Oct 1, 2026Updated 3 weeks ago
- Two-node DGX Spark/ASUS GX10 DeepSeek V4 Flash DSpark NVFP4 port for vLLM 0.25, with live dashboard and reproducible deployment.☆81Sep 13, 2026Updated last month
- To view metadata☆20Feb 18, 2026Updated 8 months ago
- Validated vLLM recipe: Qwen3.8-27B-NVFP4 at full 262,144-token context on a single RTX 5090, GPU-only (no CPU offload).☆16Aug 20, 2026Updated 2 months ago
- ComfyUI custom node for Ideogram 4 Magic Prompt and Ideogram 4 aspect-ratio resolution selection. FREE PROMPT API☆13Jun 4, 2026Updated 4 months ago
- ComfyUI custom node for local GGUF or OpenAI-compatible API driven procedural Three.js scene generation and rendering.☆18Oct 14, 2026Updated last week
- TVTest BonDriver adapter for RTL-SDR ISDB-T one-seg☆19Sep 24, 2026Updated 3 weeks ago
- ComfyUI node pack for HyperFlow [Video Rebirth's] 8-step LoRA for MiniMax-H3 (video + audio), ported onto ComfyUI's native MiniMax-H3 mod…☆57Oct 14, 2026Updated last week
- Tested MiaAI-based DeepSeek V4 Flash speed profile for two ASUS GX10s: pinned patch, settings, and benchmark helper.☆15Sep 5, 2026Updated last month
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- MiniMax H3 video + Qwen Image 2.1. Native☆27Updated this week
- Real-time talking character on a single RTX 5090 — LTX-2.5 22B + local LLM + TTS, fully local. First video ~2.6s after Enter.☆40Oct 13, 2026Updated last week
- Preview release of a unified serving engine, built for the fastest FastH3 serving.☆27Updated this week
- ☆22Sep 8, 2026Updated last month
- I am not a robot — a captcha solver for macOS: local model, Gemini vision, a stealth browser for checkbox captchas, RuCaptcha as the last…☆50Updated this week
- A python script to control the state of PoE ports on unifi switches☆13Jun 6, 2021Updated 5 years ago
- ☆12Dec 25, 2025Updated 9 months ago