From the RTX 3080 10 GB to the RTX 5070 Ti 16 GB: what changes for local AI
+6 GB of VRAM (10 → 16 GB). Of 49 models, 13 newly run well, 27 get a better file or stop offloading, and 9 stay the same.
13newly run well
27better file
9no change
+6GB more VRAM
01Newly runs well
| Model | On the RTX 3080 10 GB | On the RTX 5070 Ti 16 GB | Needed |
|---|---|---|---|
| FLUX.1 [dev] | Runs Q4_K_S | Runs well FP8 | 14.2 GB |
| FLUX.1 [schnell] | Runs Q4_K_S | Runs well FP8 | 14.2 GB |
| FLUX.1 Kontext [dev] | Runs Q4_K_M | Runs well FP8 | 14.5 GB |
| FLUX.1 Krea [dev] | Runs Q4_K_M | Runs well FP8 | 14.2 GB |
| FLUX.1 Fill [dev] | Runs Q4_K_S | Runs well Q8_0 | 15.3 GB |
| FLUX.2 [klein] 9B | Runs Q5_K_M | Runs well FP8 | 11.7 GB |
| Krea 2 (Turbo) | Tight Q3_K_M | Runs well FP8 | 15.7 GB |
| Boogu-Image (Turbo) | Offload only Q5_1 | Runs well FP8 | 12.9 GB |
| ERNIE-Image (Turbo) | Runs Q6_K | Runs well Q8_0 | 11.0 GB |
| HiDream-O1-Image | Offload only FP8 | Runs well FP8 | 10.9 GB |
| Stable Diffusion 3.5 Large | Runs Q5_1 | Runs well Q8_0 | 11.1 GB |
| Chroma1-HD | Runs Q6_K | Runs well FP8 | 11.5 GB |
| HunyuanVideo 1.5 | Runs Q4_K_M | Runs well FP8 | 12.6 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 3080 10 GB | On the RTX 5070 Ti 16 GB | Needed |
|---|---|---|---|
| Qwen-Image-Edit (2511) | Offload only Q2_K | Tight Q3_K_M | 12.9 GB |
| Ideogram 4 | Offload only Q4_1 | Runs Q4_1 | 14.7 GB |
| HunyuanImage 2.1 | Offload only Q2_K | Runs Q4_K_M | 14.6 GB |
| Wan 2.1 T2V 14B | Offload only Q3_K_M | Runs Q5_K_M | 15.6 GB |
| Wan 2.1 I2V 14B 480P | Offload only Q4_K_M | Runs Q4_K_M | 15.6 GB |
| Wan 2.1 I2V 14B 720P | Offload only Q4_K_M | Tight Q3_K_M | 15.4 GB |
| Wan 2.1 VACE 14B | Offload only Q4_K_M | Tight Q3_K_S | 12.6 GB |
| Wan 2.2 Animate 14B | Offload only Q2_K | Tight Q3_K_M | 13.9 GB |
| Wan Animate 2 (14B) | Offload only Q2_K | Tight Q3_K_M | 13.9 GB |
| Wan 2.2 S2V 14B | Offload only Q4_K_M | Tight Q2_K | 14.3 GB |
| SCAIL-2 (character animation) | Offload only Q4_K_M | Tight Q3_K_M | 14.4 GB |
| HunyuanVideo (13B, original) | Offload only Q3_K_M | Runs Q6_K | 15.3 GB |
| LTX-2 (19B) | Offload only Q4_K_M | Tight Q3_K_M | 14.9 GB |
| LTX-2.3 (22B) | Offload only Q4_K_M | Tight Q3_K_M | 15.6 GB |
| LTX-2.5 (22B) | Offload only Q4_K_M | Tight Q2_K | 13.6 GB |
| MiniMax H3 Pruned | Offload only Q4_K_M | Tight Q3_K_M | 14.7 GB |
| FLUX.2 [dev] | Not practical Q2_K | Offload only Q2_K | 16.2 GB |
| Qwen-Image | Tight Q2_K | Runs Q4_K_M | 15.9 GB |
| Z-Image Turbo | Runs well Q8_0 | Runs well 16-bit | 14.3 GB |
| Z-Image (base) | Runs well Q8_0 | Runs well 16-bit | 14.3 GB |
| Mage-Flow (Microsoft) | Runs well INT8 | Runs well 16-bit | 10.0 GB |
| HiDream-I1 (Full) | Tight Q2_K | Runs Q5_K_M | 15.8 GB |
| HiDream-I1 (Dev) | Tight Q2_K | Runs Q5_K_M | 15.8 GB |
| Wan 2.2 T2V A14B | Tight Q2_K | Runs Q5_K_M | 15.1 GB |
| Wan 2.2 I2V A14B | Tight Q2_K | Runs Q5_K_M | 15.1 GB |
| Wan 2.2 TI2V 5B | Runs well Q8_0 | Runs well 16-bit | 13.8 GB |
| LTX-Video 13B (0.9.8) | Tight Q2_K | Runs Q6_K | 15.2 GB |
03No change in what fits
FLUX.2 klein 4B Runs wellQwen-Image 2.1 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 wellMiniMax H3 Offload only
Same verdict and same file on both cards. Speed can still differ.
04Speed and features
Memory bandwidth goes from 760 to 896 GB/s (×1.18). For models that fit on both cards, bandwidth and compute decide the speed; this ratio is a rough first guide, not a benchmark. The RTX 5070 Ti 16 GB computes FP8 natively, so FP8 files run faster there than on the RTX 3080 10 GB, which only uses them to save memory. It also adds FP4 (NVFP4) hardware, for models that ship NVFP4 files.