From the RTX 5060 Ti 16 GB to the RTX 3090 24 GB: what changes for local AI
+8 GB of VRAM (16 → 24 GB). Of 49 models, 18 newly run well, 14 get a better file or stop offloading, and 17 stay the same.
18newly run well
14better file
17no change
+8GB more VRAM
01Newly runs well
| Model | On the RTX 5060 Ti 16 GB | On the RTX 3090 24 GB | Needed |
|---|---|---|---|
| Qwen-Image | Runs Q4_K_M | Runs well FP8 | 23.2 GB |
| Qwen-Image-Edit (2511) | Tight Q3_K_M | Runs well FP8 | 23.5 GB |
| Ideogram 4 | Runs Q4_1 | Runs well Q8_0 | 22.6 GB |
| HiDream-I1 (Full) | Runs Q5_K_M | Runs well Q8_0 | 21.5 GB |
| HiDream-I1 (Dev) | Runs Q5_K_M | Runs well Q8_0 | 21.5 GB |
| HunyuanImage 2.1 | Runs Q4_K_M | Runs well Q8_0 | 23.1 GB |
| Wan 2.1 T2V 14B | Runs Q5_K_M | Runs well Q8_0 | 20.2 GB |
| Wan 2.1 I2V 14B 480P | Runs Q4_K_M | Runs well Q8_0 | 22.4 GB |
| Wan 2.1 I2V 14B 720P | Tight Q3_K_M | Runs well FP8 | 23.2 GB |
| Wan 2.1 VACE 14B | Tight Q3_K_S | Runs well Q8_0 | 23.5 GB |
| Wan 2.2 T2V A14B | Runs Q5_K_M | Runs well Q8_0 | 19.7 GB |
| Wan 2.2 I2V A14B | Runs Q5_K_M | Runs well Q8_0 | 19.7 GB |
| Wan 2.2 Animate 14B | Tight Q3_K_M | Runs well FP8 | 22.6 GB |
| Wan Animate 2 (14B) | Tight Q3_K_M | Runs well Q8_0 | 23.4 GB |
| Wan 2.2 S2V 14B | Tight Q2_K | Runs well FP8 | 21.2 GB |
| SCAIL-2 (character animation) | Tight Q3_K_M | Runs well Q8_0 | 23.4 GB |
| HunyuanVideo (13B, original) | Runs Q6_K | Runs well Q8_0 | 18.3 GB |
| LTX-Video 13B (0.9.8) | Runs Q6_K | Runs well Q8_0 | 18.3 GB |
“Runs well” means a 16-bit or 8-bit file fits entirely in VRAM.
02A better file, or less offloading
| Model | On the RTX 5060 Ti 16 GB | On the RTX 3090 24 GB | Needed |
|---|---|---|---|
| FLUX.2 [dev] | Offload only Q2_K | Runs Q4_K_M | 23.4 GB |
| MiniMax H3 (33B) | Offload only Q4_K_M | Tight Q3_K_M | 21.4 GB |
| FLUX.2 [klein] 9B | Runs well FP8 | Runs well 16-bit | 20.5 GB |
| Qwen-Image 2.1 | Runs well Q8_0 | Runs well 16-bit | 16.5 GB |
| Boogu-Image (Turbo) | Runs well FP8 | Runs well 16-bit | 23.2 GB |
| ERNIE-Image (Turbo) | Runs well Q8_0 | Runs well 16-bit | 18.4 GB |
| HiDream-O1-Image | Runs well FP8 | Runs well 16-bit | 19.2 GB |
| Stable Diffusion 3.5 Large | Runs well Q8_0 | Runs well 16-bit | 18.8 GB |
| Chroma1-HD | Runs well FP8 | Runs well 16-bit | 20.1 GB |
| HunyuanVideo 1.5 | Runs well FP8 | Runs well 16-bit | 21.0 GB |
| LTX-2 (19B) | Tight Q3_K_M | Runs Q6_K | 20.8 GB |
| LTX-2.3 (22B) | Tight Q3_K_M | Runs Q6_K | 22.6 GB |
| LTX-2.5 (22B) | Tight Q2_K | Runs Q6_K | 23.5 GB |
| MiniMax H3 Pruned | Tight Q3_K_M | Runs Q6_K | 22.5 GB |
03No change in what fits
FLUX.1 dev Runs wellFLUX.1 schnell Runs wellFLUX.1 Kontext Runs wellFLUX.1 Krea Runs wellFLUX.1 Fill Runs wellFLUX.2 klein 4B Runs wellKrea 2 Runs wellZ-Image Turbo Runs wellZ-Image Runs wellMage-Flow Runs wellLumina 2.0 Runs wellSD 3.5 Medium Runs wellSDXL Runs wellIllustrious / Pony Runs wellSD 1.5 Runs wellWan 2.1 1.3B Runs wellWan 2.2 5B Runs well
Same verdict and same file on both cards. Speed can still differ.
04Speed and features
Memory bandwidth goes from 448 to 936 GB/s (×2.09). For models that fit on both cards, bandwidth and compute decide the speed; this ratio is a rough first guide, not a benchmark.