The most efficient one-page LoRA trainer for Anima 2B. Optimized for 6GB+ VRAM, featuring a smart dataset analyzer and real-time previews.
-
Updated
May 31, 2026 - Python
#
low-vram
Here are 27 public repositories matching this topic...
One-click Windows installer for Z-Image Turbo AI image generation. Optimized for low-VRAM GPUs (4GB+). Features Gradio web UI, automatic setup, and GGUF model support.
image-generation windows-installer one-click-installer ai-tools stable-diffusion ai-image-generation gguf gradio-ui low-vram z-image-turbo
-
Updated
Jun 11, 2026 - Python
Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.
python knowledge-graph semantic-search postgress rag vector-search edge-ai network-routing setfit pgvector advanced-rag graphrag rust-optimization agentic-rag grounded-reasoning low-vram hierarchical-rag anti-hallucination vector-databse
-
Updated
Feb 11, 2026 - Python
A ComfyUI Workflow for low vram users
work text-to-image video-generation image-to-video stable-diffusion gguf lowvram comfyu low-vram wan22
-
Updated
Jan 26, 2026
"Adaptive Hybrid Quantization Framework for deploying 7B+ LLMs on low-VRAM devices (e.g., GTX 1050). Features surgical block alignment and Numba-accelerated inference.
python machine-learning cuda inference transformer attention numba quantization deep-tech llm gguf low-vram qkv
-
Updated
Jan 14, 2026 - Python
Taiwanese Hokkien (Taigi) speech-to-text transcriber - MediaTek Breeze-ASR-26 with faster-whisper, tuned for RTX 3050 4GB low-VRAM GPUs. Gradio UI, CLI, Docker, SRT/VTT/TXT/JSON.
mediatek pytorch speech-recognition automatic-speech-recognition speech-to-text gradio whisper asr hokkien taiwanese chinese-speech-recognition subtitle-generator taigi faster-whisper ctranslate2 low-vram breeze-asr rtx-3050
-
Updated
Jun 8, 2026 - Python
llama.cpp fork tuned for running modern models (Gemma-4, Qwen3.x) at full context on 12 GB Turing GPUs (RTX 2060/2070/2080, T4). TurboQuant KV cache (KTQ+VTQ, 2.78 bpw f16-quality), SWA-aware KV, MTP+n-gram speculation.
-
Updated
Jun 15, 2026 - C++
🎥 Generate high-quality videos on budget hardware with the Wan 2.2 14B Low-VRAM Workflow for ComfyUI, optimized for smooth performance and quick results.
work text-to-image video-generation image-to-video stable-diffusion gguf lowvram comfyu low-vram wan22
-
Updated
Jun 15, 2026
Lightweight 6GB VRAM Gradio web app with auto-installer for running AuraFlow locally — no cloud, no clutter.
python open-source image-generation webui gradio text-to-image stable-diffusion diffusers local-inference generative-ai ai-image-generator auraflow low-vram
-
Updated
Jun 7, 2025 - Python
Simple FP16 image upscaler for all GPUs (low-mid end users)
gui ai image-processing lite x4 tkinter-python esrgan upscaler onnxruntime portable-app directml low-vram
-
Updated
Mar 28, 2026 - Python
Contains the notebooks and workflows configured to run inference from Wan 2.2 Animate with ComfyUI on Kaggle T4 GPUs smoothly
-
Updated
Nov 27, 2025 - Jupyter Notebook
Perkunas AI Training Platform is a memory-aware model training and serving system for serious language model experimentation under tight hardware limits. It combines streaming training, rich telemetry, guarded recovery, checkpoint export, and OpenAI-compatible serving.
machine-learning ai deep-learning telemetry cuda inference pytorch language-models memory-efficient model-training training-platform huggingface checkpointing llm vllm low-vram vram-optimization
-
Updated
May 17, 2026 - Python
Unofficial AMD ROCm low-VRAM fork of Hunyuan3D-2.1 — 6-view PBR texture at ~10.5 GB peak on 20 GB AMD. See README_AMD_ROCM.md.
-
Updated
May 21, 2026 - Python
Audit local LLM function calling and agentic reliability. Visual tool-use benchmarking for quantized models on YOUR hardware.
open-source gradio fan-out multi-gpu ai-safety tool-use model-benchmarking llm local-inference function-calling lm-studio llm-evaluation agentic-ai open-weight low-vram constraint-compliance quantization-testing
-
Updated
Apr 4, 2026 - Python
A privacy-first Generative AI pipeline for prototyping 3D-style game assets on consumer hardware. Optimized for low-VRAM (4GB) GPUs using PyTorch, Diffusers, and Streamlit.
-
Updated
Dec 6, 2025 - Python
Lightweight Stable Diffusion engine with plugin-based pipelines, VRAM-safe execution, and full 4GB GPU support.
webgl nextjs pytorch gpu-optimization fastapi ai-art framer-motion stable-diffusion generative-ai low-vram
-
Updated
Mar 31, 2026 - Python
Wan2.2 (14B) Image-to-Video ComfyUI workflow optimized for 8GB VRAM. Features 2-stage dynamic GGUF switching to completely avoid OOM (<7.0GB peak).
-
Updated
Jun 9, 2026 - HTML
A depth-guided, category-conditioned lightweight geometry completion network for indoor furniture reconstruction on consumer low-VRAM GPUs — 35M parameters, 88 MB, 0.5 s per object
-
Updated
May 10, 2026
ComfyUI nodes for Ideogram GGUF inference on 8GB VRAM.
-
Updated
Jun 11, 2026 - Python
Run Stable Diffusion locally on Intel iGPU/CPU with OpenVINO acceleration. Uncensored, Low VRAM, No NVIDIA required!
-
Updated
Jun 8, 2026 - Python
Improve this page
Add a description, image, and links to the low-vram topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the low-vram topic, visit your repo's landing page and select "manage topics."