§01·index · /recipes
Recipes
20 community-tested setups for running open-weights AI models on real consumer GPUs.
- imageintermediate21GB+
Qwen-Image on RTX 5090: 20B Text-to-Image via ComfyUI FP8 (Blackwell Native Path)
- imagebeginner9GB+
Flux.2 Klein 4B on RTX 5090: FP8 1.2-Second Generation, Blackwell-Native Speed Win
- imageintermediate18GB+
LongCat-Image (base T2I) on RTX 5090: Bilingual 6B Text-to-Image via diffusers BF16 with 14 GB Headroom
- imageintermediate24GB+
Chroma1-Base (V48) on RTX 5090: Uncensored 8.9B FLUX.1-Schnell De-Distillation via Diffusers BF16
- imageintermediate17GB+
HiDream-O1-Image on RTX 5090: 2048×2048 Text-to-Image with MXFP8 Blackwell-Native Acceleration in ComfyUI
- llmintermediate29GB+
Qwen3-32B on RTX 5090: Q6_K_XL GGUF via llama.cpp (with AWQ-INT4 + 128K context alternative)
- llmintermediate29GB+
Gemma 4 26B A4B-it on RTX 5090: Q8_0 Quality Tier via ggml-org GGUF + llama.cpp
- llmbeginner10GB+
DeepSeek-R1-Distill-Qwen-14B on RTX 5090: 128K Reasoning Context Unlocked
- llmintermediate17GB+
Qwen3-14B on RTX 5090: FP8 via vLLM with Native Blackwell Acceleration
- llmbeginner6GB+
Qwen3-8B on RTX 5090: Q4_K_M GGUF with 26 GB of Headroom for Colocation, BF16, or Full 131K Context
- llmbeginner16GB+
gpt-oss 20B on RTX 5090: MXFP4 Chat at 298 tok/s via Ollama or vLLM
- videointermediate14GB+
HunyuanVideo-1.5 on RTX 5090: 480p Step-Distilled I2V with an 8 GB Headroom Unlock
- videointermediate22GB+
LightX2V on RTX 5090: 4-Step Text-to-Video with Distilled Wan2.1-14B (Blackwell-Native FP8 + Future NVFP4 Path)
- videointermediate24GB+
Wan 2.2 T2V-A14B on RTX 5090: 720p text-to-video in ComfyUI with FP8 scaled weights (Blackwell)
- videointermediate20GB+
CogVideoX 1.5 5B on RTX 5090: 1360x768 Text-to-Video, No-Sequential-Offload Path
- videointermediate22GB+
Mochi 1 on RTX 5090: 85-frame 480p Text-to-Video with Diffusers
- videointermediate8GB+
Wan 2.2 TI2V-5B on RTX 5090: 720p Text/Image-to-Video in ComfyUI
- multimodalbeginner20GB+
Gemma 4 E4B on RTX 3090: Multimodal Inference via BF16 (with 16 GB of Headroom to Spend)
- 3dintermediate12GB+
Waypoint 1.5 on RTX 3090: Real-Time Interactive World Model at 720p, 30 FPS
- imagebeginner13GB+
Flux.2 Klein 4B on RTX 3090: BFL-Recommended ~13 GB CPU-Offload Path for 4-Step Text-to-Image