RTX 4090 24 GB vs RTX 3090 24 GB for local AI
Both have 24 GB, so the same model files fit on both — the memory verdicts are identical for 49 of 49 models. The difference is speed and file choice: the RTX 4090 24 GB computes FP8 natively, so FP8 files run faster there.
RTX 4090 24 GB
- VRAM
- 24 GB
- Memory
- GDDR6X
- Bandwidth
- 1008 GB/s
- Architecture
- Ada Lovelace
- FP8 compute
- Yes
- Launch price
- $1,599
VS
RTX 3090 24 GB
- VRAM
- 24 GB
- Memory
- GDDR6X
- Bandwidth
- 936 GB/s
- Architecture
- Ampere
- FP8 compute
- No
- Launch price
- $1,499
01Model by model
| Model | RTX 4090 24 GB | RTX 3090 24 GB | ||
|---|---|---|---|---|
| image models | ||||
| FLUX.1 dev | Runs well FP8 | Runs well Q8_0 | ||
| FLUX.1 schnell | Runs well FP8 | Runs well Q8_0 | ||
| FLUX.1 Kontext | Runs well FP8 | Runs well Q8_0 | ||
| FLUX.1 Krea | Runs well FP8 | Runs well Q8_0 | ||
| FLUX.1 Fill | Runs well Q8_0 | Runs well Q8_0 | ||
| FLUX.2 dev | Runs Q4_K_M | Runs Q4_K_M | ||
| FLUX.2 klein 9B | Runs well 16-bit | Runs well 16-bit | ||
| FLUX.2 klein 4B | Runs well 16-bit | Runs well 16-bit | ||
| Krea 2 | Runs well FP8 | Runs well Q8_0 | ||
| Qwen-Image | Runs well FP8 | Runs well FP8 | ||
| Qwen-Image-Edit | Runs well FP8 | Runs well FP8 | ||
| Qwen-Image 2.1 | Runs well 16-bit | Runs well 16-bit | ||
| Z-Image Turbo | Runs well 16-bit | Runs well 16-bit | ||
| Z-Image | Runs well 16-bit | Runs well 16-bit | ||
| Ideogram 4 | Runs well FP8 | Runs well Q8_0 | ||
| Boogu-Image | Runs well 16-bit | Runs well 16-bit | ||
| ERNIE-Image | Runs well 16-bit | Runs well 16-bit | ||
| HiDream-O1 | Runs well 16-bit | Runs well 16-bit | ||
| Mage-Flow | Runs well 16-bit | Runs well 16-bit | ||
| Lumina 2.0 | Runs well 16-bit | Runs well 16-bit | ||
| HiDream-I1 Full | Runs well FP8 | Runs well Q8_0 | ||
| HiDream-I1 | Runs well FP8 | Runs well Q8_0 | ||
| SD 3.5 Large | Runs well 16-bit | Runs well 16-bit | ||
| SD 3.5 Medium | Runs well 16-bit | Runs well 16-bit | ||
| Chroma1-HD | Runs well 16-bit | Runs well 16-bit | ||
| SDXL | Runs well 16-bit | Runs well 16-bit | ||
| Illustrious / Pony | Runs well 16-bit | Runs well 16-bit | ||
| SD 1.5 | Runs well 16-bit | Runs well 16-bit | ||
| HunyuanImage 2.1 | Runs well FP8 | Runs well Q8_0 | ||
| video models | ||||
| Wan 2.1 14B | Runs well FP8 | Runs well Q8_0 | ||
| Wan 2.1 1.3B | Runs well 16-bit | Runs well 16-bit | ||
| Wan 2.1 I2V 480P | Runs well FP8 | Runs well Q8_0 | ||
| Wan 2.1 I2V 720P | Runs well FP8 | Runs well FP8 | ||
| Wan VACE 14B | Runs well Q8_0 | Runs well Q8_0 | ||
| Wan 2.2 T2V | Runs well FP8 | Runs well Q8_0 | ||
| Wan 2.2 I2V | Runs well FP8 | Runs well Q8_0 | ||
| Wan 2.2 5B | Runs well 16-bit | Runs well 16-bit | ||
| Wan 2.2 Animate | Runs well FP8 | Runs well FP8 | ||
| Wan Animate 2 | Runs well Q8_0 | Runs well Q8_0 | ||
| Wan 2.2 S2V | Runs well FP8 | Runs well FP8 | ||
| SCAIL-2 | Runs well FP8 | Runs well Q8_0 | ||
| HunyuanVideo 13B | Runs well FP8 | Runs well Q8_0 | ||
| LTX-Video 13B | Runs well FP8 | Runs well Q8_0 | ||
| HunyuanVideo 1.5 | Runs well 16-bit | Runs well 16-bit | ||
| LTX-2 | Runs Q6_K | Runs Q6_K | ||
| LTX-2.3 | Runs Q6_K | Runs Q6_K | ||
| LTX-2.5 | Runs Q6_K | Runs Q6_K | ||
| MiniMax H3 | Tight Q3_K_M | Tight Q3_K_M | ||
| MiniMax H3 Pruned | Runs Q6_K | Runs Q6_K | ||
Highlighted: the GPU that runs a better file for that model. Launch prices are the maker’s original list prices, not today’s street prices. Calculated from real file sizes; how the numbers work.
02Score
43run well on RTX 4090 24 GB
43run well on RTX 3090 24 GB
0better on RTX 4090 24 GB
0better on RTX 3090 24 GB