§01·spec · /gpus
RTX 3060
nvidia30 series12GB VRAM
40 open-weights AI models run on the RTX 3060 — see which fit, how fast they go, and the VRAM each needs.
§02·models that run on this GPU
40 totalLLM · 7
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| gpt-oss 20B | 64tokens/s | 12GB | ✓ | 1benchrecipe | check ↗ |
| Qwen3-8B | 55.2tokens/s | 12GB | ✓ | 2benchesrecipe | check ↗ |
| Llama 3.1 8B | 52.2tokens/s | 10GB | ✓ | 2benchesrecipe | check ↗ |
| Qwen3 14B | 35.9tok/s | 12GB | ✓ | 3benchesrecipe | check ↗ |
| Apodex 1.1 mini | 12GB | ✓ | recipe | check ↗ | |
| Nanbeige4.2 3B | 12GB | ✓ | recipe | check ↗ | |
| Ornith 1.0 9B | 12GB | ✓ | recipe | check ↗ |
- Best speed
- 64tokens/s
- Min VRAM
- 12GB
- Evidence
- 1bench
- Best speed
- 55.2tokens/s
- Min VRAM
- 12GB
- Evidence
- 2benches
- Best speed
- 52.2tokens/s
- Min VRAM
- 10GB
- Evidence
- 2benches
- Best speed
- 35.9tok/s
- Min VRAM
- 12GB
- Evidence
- 3benches
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 12GB
Multimodal · 8
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| Gemma 4 E4B-IT | 45tokens/s | 6GB | ✓ | 1benchrecipe | check ↗ |
| Qwen3.6 35B-A3B | 38.9tok/s | 9.8GB | ✓ | 1benchrecipe | check ↗ |
| Gemma 4 26B MoE | 37.2tok/s | 10.92GB | ✓ | 1bench | check ↗ |
| Fara1.5-4B | 12GB | ✓ | recipe | check ↗ | |
| Fara1.5-9B | 12GB | ✓ | recipe | check ↗ | |
| MiniMind-O | 4GB | ✓ | recipe | check ↗ | |
| MOSS-Audio | 12GB | ✓ | recipe | check ↗ | |
| Voxtral Mini 3B | 10GB | ✓ | recipe | check ↗ |
- Best speed
- 45tokens/s
- Min VRAM
- 6GB
- Evidence
- 1bench
- Best speed
- 38.9tok/s
- Min VRAM
- 9.8GB
- Evidence
- 1bench
- Best speed
- 37.2tok/s
- Min VRAM
- 10.92GB
- Evidence
- 1bench
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 4GB
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 10GB
Image · 11
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| Anima | 7GB | ✓ | recipe | check ↗ | |
| Chroma V48 | 11GB | ✓ | recipe | check ↗ | |
| ERNIE-Image-Turbo | 10GB | ✓ | recipe | check ↗ | |
| Flux.2-Klein-4B | 8GB | ✓ | recipe | check ↗ | |
| HiDream-O1-Image | 10GB | ✓ | recipe | check ↗ | |
| Juggernaut Z | 12GB | ✓ | recipe | check ↗ | |
| Krea 2 | 12GB | ✓ | recipe | check ↗ | |
| Qwen-Image | 12GB | ✓ | recipe | check ↗ | |
| Qwen-Image-2.1 | 12GB | ✓ | recipe | check ↗ | |
| SD1.5 | 4GB | ✓ | recipe | check ↗ | |
| SenseNova U1 | 12GB | ✓ | recipe | check ↗ |
- Best speed
- Min VRAM
- 7GB
- Best speed
- Min VRAM
- 11GB
- Best speed
- Min VRAM
- 10GB
- Best speed
- Min VRAM
- 8GB
- Best speed
- Min VRAM
- 10GB
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 12GB
- Best speed
- Min VRAM
- 4GB
- Best speed
- Min VRAM
- 12GB
Video · 3
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| LightX2V | 12GB | ✓ | recipe | check ↗ | |
| MiniMax H3 (Hailuo 3) | 12GB | ✓ | recipe | check ↗ | |
| Wan 2.2 TI2V-5B | 8GB | ✓ | recipe | check ↗ |
3D · 1
TTS · 6
Music · 2
| Model | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|
| ACE-Step 1.5 XL | 8GB | ✓ | recipe | check ↗ | |
| Foundation-1 | 8GB | ✓ | recipe | check ↗ |
§03·tested recipes
showing 6 of 39- imageintermediate12GB+recipe
Qwen-Image-2.1 on RTX 3060: int8 text-to-image and editing in ComfyUI (Ampere sm_86, 12 GB)
- llmadvanced12GB+recipe
Apodex 1.1 mini on RTX 3060: a 35B-A3B agent model on 12GB via expert offload
- llmadvanced12GB+recipe
Qwen3.6-35B-A3B on RTX 3060: 38.9 tok/s from a 12GB card via MoE expert CPU-offload
- llmintermediate12GB+recipe
Nanbeige4.2-3B on RTX 3060: Q8_0 weights and a 65,536-token cache in 12 GB
- videoadvanced12GB+recipe
MiniMax H3 on RTX 3060: 12 GB video+audio in ComfyUI, measured on this card
- multimodaladvanced12GB+recipe
Fara1.5-9B on RTX 3060: a 12GB Browser Computer-Use Agent at Q5_K_M with llama.cpp