low-vram repositories
Trending repositories tagged low-vram, ranked by trending score. Updated daily.
-
1
MakazhanAlpamys/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
GitHub · Python · 10,683 stars · 1,777 forks · +43 stars in 24 hours · Trending score 3.38
-
2
alexturkey/voxcpm2-turkce-ses-tasarimi
Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices.
GitHub · Python · 472 stars · 70 forks · +25 stars in 24 hours · Trending score 2.69
-
3
alexturkey/z-image-turbo-pascal-4gb
Sınırsız Foto: Z-Image-Turbo (Q8_0, full quality) on a 4 GB GTX 1050 Ti laptop with 16 GB RAM. stable-diffusion.cpp + cuDNN VAE, Windows, every number measured. Unofficial. Not affiliated with Tongyi-MAI, leejet or NVIDIA.
GitHub · Python · 186 stars · 36 forks · +34 stars in 24 hours · Trending score 1.69
-
4
yanfei0725/dsh-qwen-paint
DSH 插件 / DeepSeek Harness:视频 / 生图 / TTS 全能 · 本机运行(QQ 交流群 454707710)。★ 0.33.0 起许可★ 0.33.0 起许可改为 BSL 1.1(BUSL-1.1,非 OSI 开源许可):除托管/代管服务与直接竞品捆绑两类「竞争性使用」外免费生产使用,2030-11-15 转 Apache-2.0;0.32.1 及更早仍 MIT、不追溯。★ 1.0.0:选模型「假成功」根治(拒绝时如实回未生效 + ★ 1.0.0:选模型「假成功」根治(拒绝时如实回未生效 + 原因,不再无条件报已选)、优化面板与素材库白条同源修复(持久化缓存
GitHub · JavaScript · 45 stars · 0 forks · +6 stars in 24 hours · Trending score 1.46
-
5
alexturkey/wan22-pascal-4gb
Wan 2.2 TI2V-5B video generation on a 4 GB GTX 1050 Ti (Pascal): stable-diffusion.cpp patches, byte-identical speedups, recipe and agent-readable install guide
GitHub · Python · 29 stars · 13 forks · +15 stars in 24 hours · Trending score 1.42
-
6
AcademiaSD/AcademiaSD_LoRAlab-TrainerStudio
Train LoRAs for Qwen-Image 2.1, FLUX.2 Klein 9B, FLUX.3 Image Klein, Krea 2, Z-Image, MOSS-Image, ERNIE-Image, Ideogram 4, Anima, SDXL (Pony, Illustrious, NoobAI), LTX 2.3, MiniMax-H3, and more on NVIDIA GPUs from 4–8 GB VRAM. One install, one launcher, NF4 models. Windows, Linux and RunPod.
GitHub · Python · 152 stars · 13 forks · +1 stars in 24 hours · Trending score 1.00
-
7
IbrahimSiddiqui007/moe-cache
Run Mixture-of-Experts LLMs (Qwen3, gpt-oss, GLM, DeepSeek) bigger than your RAM with llama.cpp: hot experts cached in RAM, the rest streamed from SSD. Windows (Vulkan/AMD, NVIDIA) and Linux, long context, coding agents.
GitHub · Python · 22 stars · 1 forks · 0 stars in 24 hours · Trending score 0.19
-
8
Randozart/VITRIOL
Experimental local LLM inference for old hardware: in-tree llama.cpp fork, sparse KV, MTP, VRAM governor, Rust tooling.
GitHub · C++ · 39 stars · 3 forks · 0 stars in 24 hours · Trending score 0.10
-
9
0937BOY/minimax-h3-8gb-benchmark
MiniMax-H3 reference-to-video benchmark on an 8 GB RTX 3050: 0.5 / 0.6 / 0.7 MP presets with wall-clock timings and VRAM peaks, plus a minimal 23-node ComfyUI workflow.
GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.04
-
10
Jit-Roy/WeeLLM
WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.
GitHub · Python · 149 stars · 13 forks · 0 stars in 24 hours · Trending score 0.01
-
11
IvenKooLab/minimax-h3-turing
MiniMax H3 video generation on 2080Ti 22G (Turing sm_75) - field-tested handbook, workflows & FAQ
GitHub · Python · 22 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00
-
12
Mats2208/qwen-image-local
Type a prompt or drop up to 10 photos: Qwen-Image-2.1 renders it on your 12 GB GPU in ~35 s. Desktop app + CLI, honest benchmark vs gpt-image-2.
GitHub · Rust · 12 stars · 15 forks · 0 stars in 24 hours · Trending score 0.00
-
13
sepiablue-ai/ComfyUI-H3-X2-Stream
ComfyUI nodes for MiniMax H3: INT8 X2 VAE and asynchronous NVENC saving. 5-second 1088x1920 video with audio in about 60 s on an RTX 4070 12GB, about 30% faster than the FP16 X2 VAE.
GitHub · Python · 38 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
14
squadsmokebasin/vram-optimization-2026-gpu-memory-performance-toolkit
VRAM Optimization 2026 gaming toolkit for GPU memory tracking, texture profiles, VRAM usage analysis, stutter troubleshooting and performance benchmarks.
GitHub · 13 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
15
harlixay7/Kinoloom
A local AI film studio for one Windows PC with an 8 GB NVIDIA card. Write the story, cast the people and render the shots with LTX-2.5, MiniMax H3 (bring your own weights) and Qwen-Image 2.1. It joins short clips into long takes inside the model. Built on ComfyUI.
GitHub · Python · 24 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00
-
16
alexturkey/VideoTurko
MiniMax H3 on a 4 GB GTX 1050 Ti: stable-diffusion.cpp memory patches, up to 209 frames (8.7 s) in one pass
GitHub · PowerShell · 55 stars · 13 forks · Trending score 0.10
-
17
KlockTX/KlockUI
零门槛开箱即用的 ComfyUI 本地 WebUI:选模型、写描述、点生成,采样器与 LoRA 按架构自动配好。为 8–16GB 单卡设计,纯本地、免账号。
GitHub · JavaScript · 24 stars · 3 forks · Trending score 0.10