§01·index · /recipes
Recipes
1031 community-tested setups for running open-weights AI models on real consumer GPUs.page 11 of 11
- imageintermediate16GB+
Chroma V48 on RTX 5060 Ti: Uncensored 8.9B Flux.1-Schnell De-Distillation via GGUF in ComfyUI
- multimodalintermediate12GB+
MOSS-Audio 4B-Instruct on RTX 5060 Ti: local audio understanding in ~12 GB
- videointermediate8GB+
Wan 2.2 TI2V-5B on RTX 5060 Ti: 720p Text/Image-to-Video in ComfyUI
- imageintermediate13GB+
Qwen-Image on RTX 5060 Ti: 20B Text-to-Image via GGUF Quantization
- ttsbeginner2GB+
Kokoro TTS on RTX 5060 Ti: 82M-Parameter Text-to-Speech, 54 Voices, Under 3 GB VRAM
- ttsbeginner8GB+
VoxCPM2 on RTX 5060 Ti: 30-Language 48kHz Voice Cloning in ~8 GB VRAM
- videointermediate8GB+
LightX2V on RTX 5060 Ti: 4-Step Text-to-Video with Distilled Wan2.1-14B
- videoadvanced16GB+
Sulphur 2 on RTX 5060 Ti: Uncensored LTX-2.3 Video via GGUF in ComfyUI
- imageintermediate16GB+
Juggernaut Z on RTX 5060 Ti: Cinematic Photoreal Fine-Tune of Z-Image Base
- multimodalintermediate10GB+
Voxtral Mini 3B on RTX 5060 Ti: local speech understanding in ~9.5 GB
- imageintermediate10GB+
HiDream-O1-Image on RTX 5060 Ti: 2048×2048 Text-to-Image with FP8 in ComfyUI
- 3dintermediate10GB+
Hunyuan3D-2.1 on RTX 5060 Ti: Image-to-Mesh 3D Generation (Shape-Only)
- multimodalintermediate4GB+
MiniMind-O on RTX 5060 Ti: 0.1B Omni Model (Text + Speech + Image In/Out)
- ttsbeginner5GB+
VoxCPM on RTX 5060 Ti: Zero-Shot Voice Cloning TTS in ~5 GB VRAM
- specializedintermediate3GB+
KiMoDo on RTX 5060 Ti: Text-to-3D-Motion Generation Guide
- 3dintermediate16GB+
Waypoint 1.5 on RTX 5060 Ti: Real-Time Interactive World Model at 720p
- videoadvanced16GB+
LTX-2.3 on RTX 5060 Ti: GGUF Video Generation in ComfyUI
- imageintermediate13GB+
Flux.2 Klein 4B on RTX 5060 Ti: ComfyUI & Diffusers Setup
- imagebeginner7GB+
Anima 2B on RTX 5060 Ti: Native ComfyUI Anime Text-to-Image
- imageintermediate12GB+
ERNIE-Image-Turbo on RTX 5060 Ti: 8-step text-to-image via GGUF in ComfyUI
- imageintermediate16GB+
Z-Image Turbo on RTX 5060 Ti: 8-Step Text-to-Image with Diffusers or ComfyUI
- specializedbeginner4GB+
SAM 3 on RTX 5060 Ti: Promptable Image and Video Segmentation
- videobeginner8GB+
Wan 2.1 T2V on RTX 4090: Local Video Generation Guide
- 3dintermediate16GB+
TRELLIS on RTX 4090: High-Fidelity Image to 3D
- llmintermediate12GB+
Qwen3-30B-A3B on RTX 4070: Local MoE LLM via CPU-Offload
- ttsbeginner0GB+
Kokoro TTS: Lightweight Text-to-Speech That Runs on Anything
- 3dintermediate12GB+
Hunyuan3D-2 on RTX 4090: Image to 3D Model Guide
- imagebeginner16GB+
Flux.1 Dev on RTX 5060 Ti: ComfyUI Setup Guide
- ttsbeginner4GB+
F5-TTS: Zero-Shot Voice Cloning with 5 Seconds of Audio
- videointermediate10GB+
CogVideoX 1.5 on RTX 4070: High-Quality Local Video Guide
- imagebeginner24GB+
Flux.1 Dev on RTX 4090: ComfyUI Image Generation Guide