§01·spec · /gpus
RTX 5080
nvidia50 series16GB VRAM
38 open-weights AI models run on the RTX 5080 — see which fit, how fast they go, and the VRAM each needs.
§02·models that run on this GPU
38 totalLLM · 6
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| gpt-oss 20B | 172.4tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| Qwen3-8B | 129.1tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| Qwen3 14B | 80.6tokens/s | 16GB | ✓ | 2benchesrecipe | check ↗ |
| Llama 3.1 8B | 10GB | ✓ | recipe | check ↗ | |
| Ornith 1.0 9B | 12GB | ✓ | recipe | check ↗ | |
| Nemotron Elastic 12B (NVFP4) | ✓ | 1bench | check ↗ |
Multimodal · 2
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| Gemma 4 E4B-IT | 6GB | ✓ | recipe | check ↗ | |
| MiniMind-O | 4GB | ✓ | recipe | check ↗ |
Image · 11
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| Anima | 7GB | ✓ | recipe | check ↗ | |
| Chroma V48 | 14GB | ✓ | recipe | check ↗ | |
| ERNIE-Image-Turbo | 12GB | ✓ | recipe | check ↗ | |
| Flux.2-Klein-4B | 13GB | ✓ | recipe | check ↗ | |
| HiDream-O1-Image | 10GB | ✓ | recipe | check ↗ | |
| Juggernaut Z | 16GB | ✓ | recipe | check ↗ | |
| Krea 2 | 16GB | ✓ | recipe | check ↗ | |
| LongCat Image | 16GB | ✓ | recipe | check ↗ | |
| Qwen-Image | 13GB | ✓ | recipe | check ↗ | |
| SenseNova U1 | 12GB | ✓ | recipe | check ↗ | |
| Z-Image Turbo | 16GB | ✓ | recipe | check ↗ |
Video · 4
3D · 3
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| Hunyuan3D | 10GB | ✓ | recipe | check ↗ | |
| TRELLIS image-large | 16GB | ✓ | recipe | check ↗ | |
| Waypoint 1.5 | 12GB | ✓ | recipe | check ↗ |
TTS · 10
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| ACE-Step 1.5 XL | 12GB | ✓ | recipe | check ↗ | |
| Foundation-1 | 8GB | ✓ | recipe | check ↗ | |
| Kokoro TTS | 2GB | ✓ | recipe | check ↗ | |
| MOSS-Audio | 12GB | ✓ | recipe | check ↗ | |
| OmniVoice | 4GB | ✓ | recipe | check ↗ | |
| OpenAudio S1 Mini | 5GB | ✓ | recipe | check ↗ | |
| Qwen3-TTS | 8GB | ✓ | recipe | check ↗ | |
| VoxCPM | 5GB | ✓ | recipe | check ↗ | |
| VoxCPM2 | 8GB | ✓ | recipe | check ↗ | |
| Voxtral Mini 3B | 10GB | ✓ | recipe | check ↗ |
§03·tested recipes
showing 6 of 37- llmintermediate12GB+recipe
Ornith 1.0 9B on RTX 5080: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp + OpenHands
- imageintermediate16GB+recipe
Krea 2 Turbo (FP8) on RTX 5080 via ComfyUI: 8-Step Text-to-Image in 16GB
- specializedintermediate3GB+recipe
KiMoDo on RTX 5080: Text-to-3D-Motion Generation Guide
- specializedbeginner4GB+recipe
SAM 3 on RTX 5080: Promptable Image and Video Segmentation
- llmbeginner10GB+recipe
Llama 3.1 8B on RTX 5080: Local Chat via Ollama or llama.cpp + Unsloth UD-Q4_K_XL GGUF
- multimodalbeginner6GB+recipe
Gemma 4 E4B on RTX 5080: Multimodal Inference via Q4_K_M GGUF (llama.cpp or Ollama — BF16 will not fit comfortably)