Search

Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.

VibeVoiceFusion is a full-stack, multi-speaker voice generation web system featuring LoRA fine-tuning, batch generation, and VRAM optimization. Based on Microsoft's VibeVoice (AR + diffusion architecture)

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

High-performance AI agent for long-horizon tasks and local models. Built on empirical research. 200k+ tokens of work inside a 64k context window. Run a full dev team in 5GB VRAM.

Stable Diffusion: webui automatic1111 download free, comfyui setup guide, sdxl checkpoint safetensors, lora model civitai, controlnet extension github. SD WebUI Forge launcher, low VRAM optimization, xformers command line arguments, python torch cuda error fix, out of memory solution, txt2img img2img, inpainting, realesrgan upscaler, local pc insta

Plug-and-play homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, host health. Built-in read-only MCP server so AI agents can explore it too.

Use your NVIDIA GPU's VRAM as swap space on Linux. Built for laptops with soldered memory and no upgrade path. If you have an RTX card sitting there with 8GB of VRAM and you're getting swapped to SSD, this puts that VRAM to work

破限本地AI女友后宫，Agent+画图语音向量数据库+live2D+桌宠+酒馆角色卡导入+webchat，QQ+Telegram双通道，8G显存可跑 uncensored Fully offline AI girlfriends harem Openclaw/Claude code/Deepseek Harness+Local LLM+GPT-SoVITS+ComfyUI image+Live2D+desktop pet+SilllyTavern Character card import+frontend | QQ & Telegram | Dynamic 8G VRAM scheduling+mem0 qdrant, can run offline

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip selected H3 transformer evaluations, with adaptive scheduling, sampler-aware support for Euler, ER-SDE, RES, SEEDS and SA-Solver, CPU/VRAM history storage, and fail-closed native fallbacks.

ComfyUI custom nodes for MiniMax H3 long-form video/audio generation with streamed Sol attention, compressed KV, adaptive VRAM guards, chunked MLP/final output, and SAFE long-sequence optimizations for limited VRAM.

Upscale long, high-resolution MiniMax H3 video on a VRAM-limited GPU in a single node.

Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data.

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

A GPU task manager for Windows, Linux, and WSL: per-process VRAM, GPU activity, and LLM model/KV-cache insights (Windows AMD and NVIDIA).