§01·spec · /gpus
RTX 4060 Ti 16GB
nvidia40 series16GB VRAM
§02·models that run on this GPU
12 total| Model | Vertical | Best speed | Min VRAM | Works | Benchmarks | |
|---|---|---|---|---|---|---|
| Llama 3.2 1B | llm | 130tokens/s | 16GB | ✓ | 1 | check ↗ |
| Flux.1 Dev | image | 92s | 16GB | ✓ | 3 | check ↗ |
| gpt-oss 20B | llm | 63.2tokens/s | 16GB | ✓ | 2 | check ↗ |
| Llama 3.1 7B | llm | 55tok/s | 16GB | ✓ | 1 | check ↗ |
| Qwen3-8B | llm | 45.8tokens/s | 16GB | ✓ | 1 | check ↗ |
| Llama 3.1 8B | llm | 34tokens/s | 16GB | ✓ | 1 | check ↗ |
| Llama 3.1 13B | llm | 30tok/s | 16GB | ✓ | 1 | check ↗ |
| Qwen3 14B | llm | 27.4tokens/s | 16GB | ✓ | 2 | check ↗ |
| Stable Diffusion XL | image | 12s | 16GB | ✓ | 1 | check ↗ |
| Llama 3.1 34B | llm | 8tok/s | 16GB | ✓ | 1 | check ↗ |
| LTX Video 2.3 | video | 16GB | ✓ | 1 | check ↗ | |
| Llama 3.1 70B | llm | 16GB | ✕ | 1 | check ↗ |
§03·tested recipes
showing 6 of 20- multimodalintermediate4GB+recipe
MiniMind-O on RTX 4060 Ti 16GB: 0.1B Omni Model with Headroom to Spare
- ttsintermediate8GB+recipe
Foundation-1 on RTX 4060 Ti 16GB: Structured Music Sample Generation
- ttsintermediate12GB+recipe
ACE-Step 1.5 XL on RTX 4060 Ti 16GB: Text-to-Music Generation in ComfyUI
- ttsbeginner2GB+recipe
Kokoro TTS on RTX 4060 Ti 16GB: 82M-Parameter Text-to-Speech, 54 Voices, Under 3 GB VRAM
- videoadvanced16GB+recipe
Sulphur 2 on RTX 4060 Ti 16GB: Uncensored LTX-2.3 Video via ComfyUI GGUF
- ttsintermediate8GB+recipe
Qwen3-TTS 1.7B-Base on RTX 4060 Ti 16GB: Multilingual Voice Cloning in 10 Languages with FlashAttention-2