§01·tested · /gpus/rtx-4090
Recipes tested on RTX 4090
47 community-tested setups — recipes whose author ran them on this exact card.
nvidia40 series24GB VRAM
- multimodalintermediate24GB+recipe
Muse Glimmer 30B on RTX 4090: vision and DFlash in llama.cpp at full 131K context
- multimodalintermediate24GB+recipe
Qwen3.8-27B on RTX 4090: 128K-context vision chat via llama.cpp Q4_K_M
- videoadvanced24GB+recipe
LTX-2.5 on RTX 4090: Fitting the 22B Audio-Video DiT in 24 GB via ComfyUI int8
- llmintermediate24GB+recipe
Nanbeige4.2-3B on RTX 4090: the full 256K context on an sm_89 llama.cpp build
- videoadvanced12GB+recipe
MiniMax H3 on RTX 4090: 24 GB video+audio, and where Ada's FP8 shows up
- multimodaladvanced24GB+recipe
Fara1.5-9B on RTX 4090: BF16 Computer-Use Agent with Vision on Ada sm_89
- multimodaladvanced16GB+recipe
Fara1.5-4B on RTX 4090: BF16 Computer-Use Agent with a 131K Window on llama.cpp
- multimodaladvanced24GB+recipe
Fara1.5-27B on RTX 4090: Q4_K_M Browser Computer-Use Agent on Ada sm_89
- multimodalintermediate10GB+recipe
Bonsai 27B on RTX 4090: the Full 262K Window Plus the Vision Tower
- llmintermediate24GB+recipe
Gemma 4 12B on RTX 4090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate24GB+recipe
Phi-4 (14B) on RTX 4090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate24GB+recipe
Mistral Nemo 12B on RTX 4090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate24GB+recipe
Mistral Small 3.2 24B on RTX 4090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmadvanced24GB+recipe
North Mini Code 1.0 on RTX 4090: Local Agentic Coding via llama.cpp + OpenHands (24GB Ada Tier)
- llmintermediate24GB+recipe
Devstral Small 2 (24B) on RTX 4090: Local Agentic Coding via llama.cpp + OpenHands (24GB, the Vendor's Named Target)
- llmadvanced24GB+recipe
Laguna XS 2.1 on RTX 4090: Local Agentic Coding via Ollama / llama.cpp + OpenHands (24GB Entry Tier)
- llmadvanced24GB+recipe
Ornith 1.0 35B on RTX 4090: Local Agentic Coding via llama.cpp + OpenHands (24GB Entry Tier)
- llmadvanced24GB+recipe
Llama 3.3 70B on RTX 4090: 70B-Class Chat on One 24 GB Card (Q4 Offload or Fully-On-GPU IQ2)
- videoadvanced24GB+recipe
LTX-2 (19B) on RTX 4090: Audio-Video in the 24 GB Gap — FP8 + Quantized Gemma, Below the 32 GB Native Floor
- videoadvanced20GB+recipe
LTX-2.3 on RTX 4090: 22B Audio-Video in the 24 GB Gap — Roomier GGUF, Still Below the 32 GB Native Floor
- imageintermediate16GB+recipe
Krea 2 Turbo (FP8) on RTX 4090 via ComfyUI: 8-Step Text-to-Image, with the Raw Tier in Reach
- multimodalbeginner20GB+recipe
Gemma 4 E4B on RTX 4090: Multimodal Inference via BF16 (with optional Q8_0 / Q4_K_M GGUF)
- 3dintermediate12GB+recipe
Waypoint 1.5 on RTX 4090: Real-Time Interactive World Model at 720p
- videointermediate24GB+recipe
LightX2V on RTX 4090: 4-Step Text-to-Video with Distilled Wan2.1-14B
- videointermediate24GB+recipe
Wan 2.2 TI2V-5B on RTX 4090: 720p Text/Image-to-Video in ComfyUI
- imagebeginner20GB+recipe
Flux.2 Klein 4B on RTX 4090: BF16 Full-Resident 4-Step Text-to-Image via Diffusers or ComfyUI
- imageintermediate16GB+recipe
Juggernaut Z on RTX 4090: Cinematic Photoreal Fine-Tune of Z-Image Base at BF16 via Diffusers or ComfyUI
- llmbeginner16GB+recipe
gpt-oss 20B on RTX 4090: MXFP4 chat via Ollama or vLLM
- llmbeginner10GB+recipe
DeepSeek-R1-Distill-Qwen-14B on RTX 4090 via Ollama Q4_K_M GGUF
- llmintermediate18GB+recipe
Gemma 4 26B A4B-it on RTX 4090: Local Multimodal Chat via Q4_K_M GGUF + llama.cpp
- llmintermediate22GB+recipe
Qwen3-32B on RTX 4090: UD-Q4_K_XL GGUF via llama.cpp
- llmbeginner10GB+recipe
Qwen3-14B on RTX 4090: Q4_K_M GGUF via Ollama or llama.cpp
- llmbeginner6GB+recipe
Qwen3-8B on RTX 4090: Q4_K_M GGUF via Ollama or llama.cpp
- imageintermediate21GB+recipe
Qwen-Image on RTX 4090: 20B Text-to-Image via ComfyUI FP8 (Native Path)
- imageintermediate18GB+recipe
LongCat-Image (base T2I) on RTX 4090: Bilingual 6B Text-to-Image via diffusers
- imageintermediate24GB+recipe
Chroma1-Base (V48) on RTX 4090: Uncensored 8.9B FLUX.1-Schnell De-Distillation via Diffusers BF16
- imageintermediate20GB+recipe
HiDream-O1-Image on RTX 4090: 2048×2048 Text-to-Image with BF16 in ComfyUI
- imagebeginner16GB+recipe
Z-Image Turbo on RTX 4090: 8-Step 1024x1024 Text-to-Image at BF16 in ~2.3s with Diffusers or ComfyUI
- llmbeginner10GB+recipe
Llama 3.1 8B on RTX 4090: Local Chat via llama.cpp + Unsloth UD-Q4_K_XL GGUF
- videointermediate14GB+recipe
HunyuanVideo-1.5 on RTX 4090: 480p Step-Distilled Text-to-Video in ~75 Seconds
- videointermediate24GB+recipe
Wan 2.2 T2V-A14B on RTX 4090: 720p text-to-video in ComfyUI with FP8 scaled weights
- videointermediate14GB+recipe
CogVideoX 1.5 5B on RTX 4090: 1360x768 Text-to-Video with Diffusers
- videointermediate20GB+recipe
Mochi 1 on RTX 4090: 49-frame 480p Text-to-Video with Diffusers
- videobeginner8GB+recipe
Wan 2.1 T2V on RTX 4090: Local Video Generation Guide
- 3dintermediate16GB+recipe
TRELLIS on RTX 4090: High-Fidelity Image to 3D
- 3dintermediate12GB+recipe
Hunyuan3D-2 on RTX 4090: Image to 3D Model Guide
- imagebeginner24GB+recipe
Flux.1 Dev on RTX 4090: ComfyUI Image Generation Guide