AMD Radeon RX 7900 XTX, AI & Machine Learning Benchmarks & Specs

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.

AI & Machine Learning benchmark results

Text Generation tok/s 5

Qwen3 4B186
Llama 3.1 8B127.9
Qwen2.5-Coder 14B69.8
Qwen3 32B36
WorkloadResultTelemetryData
Qwen3 4B186 tok/sestimatedEst.
Llama 3.1 8B127.9 tok/sestimatedEst.
Qwen2.5-Coder 14B69.8 tok/sestimatedEst.
Qwen3 32B36 tok/sestimatedEst.
Llama 3.3 70B✕ Won't fit VRAM-gated at this precisionEst.

Image Generation images/min 3

WorkloadResultTelemetryData
Stable Diffusion XL5.34 images/minestimatedEst.
Z-Image Turbo2.48 images/minestimatedEst.
FLUX.1 dev✕ Won't fit VRAM-gated at this precisionEst.

Image Editing images/min 2

WorkloadResultTelemetryData
FLUX.1 Kontext dev✕ Won't fit VRAM-gated at this precisionEst.
Qwen-Image-Edit✕ Won't fit VRAM-gated at this precisionEst.

Video Generation frames/s 2

WorkloadResultTelemetryData
LTX-Video (distilled)1.89 frames/sestimatedEst.
Wan 2.2 5B (720p)0.15 frames/sestimatedEst.
How this estimate is derived. This card hasn’t been through our bench yet, so its numbers are anchored estimates, interpolated from the 51 first-party measured cards (Bandwidth Theil-Sen ladder off NVIDIA anchors × vendor factor (LLM ×0.85, diffusion ×0.5); realistic VRAM floors). The VRAM “won’t fit” gates are exact, since they’re pure capacity limits. Confidence: low. Estimates are replaced with measured data as more silicon goes through the bench. Full methodology →

AMD Radeon RX 7900 XTX specifications

ArchitectureRDNA 3 (Navi 31)
Stream processors6,144
VRAM24GB GDDR6
Memory bus384-bit
Memory bandwidth960 GB/s
Boost clock2,500 MHz
TDP355 W
Process5nm (GPU) + 6nm (MCD)
InterfacePCIe 4.0 x16
Release date2022-12-13
Launch MSRP$999

Verdict, capable, but 24GB sets the ceiling

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.

Relative performance: where the AMD Radeon RX 7900 XTX lands

100% = this card, AI & Machine Learning headline metric (AI Score). #9 of 61 desktop cards in this vertical.

GPURelative%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

The silicon

Transistors57,700 million
Process node5 nm
Fabricated byTSMC

Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.

What this card can build

Whole-job timings, composed from our measured per-model results on this card.

WorkflowTimeEnergyBasis
24-frame storyboard10.3 minn/aestimate, 0 of 2 stages measured
Full codebase review14.3 minn/aestimate, 0 of 1 stage measured
60-second AI short film16.1 minn/aestimate, 0 of 3 stages measured
10 short social clips58.7 minn/aestimate, 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).