24GB · AI Score 6.7/100 · anchored estimate vs 51 measured cards
6.7 AI Score Includes estimates
We have not run AMD Radeon RX 7900 XTX on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure (confidence: low). On Llama 3.1 8B (Q4_K_M) AMD Radeon RX 7900 XTX should deliver about 127.9 tokens/sec. Stepping up to Qwen3 32B it should hold roughly 36 tok/s. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 24GB. For image generation, SDXL should run near 2.67 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 4 of the 12 workloads won't fit on 24GB at the tested precision, Llama 3.3 70B, FLUX.1-dev, FLUX.1 Kontext, Qwen-Image-Edit. We publish those as hard gates rather than quietly dropping to a smaller quant.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3 4B | 186 tok/s | estimated | Est. |
| Llama 3.1 8B | 127.9 tok/s | estimated | Est. |
| Qwen2.5-Coder 14B | 69.8 tok/s | estimated | Est. |
| Qwen3 32B | 36 tok/s | estimated | Est. |
| Llama 3.3 70B | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion XL | 5.34 images/min | estimated | Est. |
| Z-Image Turbo | 2.48 images/min | estimated | Est. |
| FLUX.1 dev | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Qwen-Image-Edit | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| LTX-Video (distilled) | 1.89 frames/s | estimated | Est. |
| Wan 2.2 5B (720p) | 0.15 frames/s | estimated | Est. |
| Architecture | RDNA 3 (Navi 31) |
| Stream processors | 6,144 |
| VRAM | 24GB GDDR6 |
| Memory bus | 384-bit |
| Memory bandwidth | 960 GB/s |
| Boost clock | 2,500 MHz |
| TDP | 355 W |
| Process | 5nm (GPU) + 6nm (MCD) |
| Interface | PCIe 4.0 x16 |
| Release date | 2022-12-13 |
| Launch MSRP | $999 |
AMD Radeon RX 7900 XTX scores 6.7/100, #38 of 102. It ran 8 of 12; 4 exceeded its 24GB. Figures are anchored estimates, not measurements, we flag that on every row.
100% = this card, AI & Machine Learning headline metric (AI Score). #9 of 61 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| NVIDIA GeForce RTX 4090 | 155% | 10.4 | |
| NVIDIA GeForce RTX 3090 Ti | 127% | 8.5 | |
| NVIDIA Titan RTX | 122% | 8.2 | |
| NVIDIA GeForce RTX 3090 | 115% | 7.7 | |
| AMD Radeon RX 7900 XTX | 100% | 6.7 | |
| AMD Radeon RX 7900 XT | 93% | 6.2 | |
| GeForce RTX 4080 Super | 81% | 5.4 | |
| GeForce RTX 5080 | 73% | 4.9 | |
| NVIDIA GeForce RTX 4080 | 70% | 4.7 |
Same card, other workloads: AMD Radeon RX 7900 XTX Gaming benchmarks
← All AI & Machine Learning GPU rankings
| Transistors | 57,700 million |
| Process node | 5 nm |
| Fabricated by | TSMC |
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
| Workflow | Time | Energy | Basis |
|---|---|---|---|
| 24-frame storyboard | 10.3 min | n/a | estimate, 0 of 2 stages measured |
| Full codebase review | 14.3 min | n/a | estimate, 0 of 1 stage measured |
| 60-second AI short film | 16.1 min | n/a | estimate, 0 of 3 stages measured |
| 10 short social clips | 58.7 min | n/a | estimate, 0 of 3 stages measured |
Can't run: 40-product photo shoot (needs FLUX.1 Kontext dev), 6-panel comic page (needs FLUX.1 dev), 20 long-form articles (needs Llama 3.3 70B), Character sheet, 12 poses (needs FLUX.1 dev), 100-photo restoration batch (needs FLUX.1 Kontext dev), 100-photo restore and enlarge (needs FLUX.1 Kontext dev).