Home › GPUs & Macs › AMD Radeon RX 7900 XTX vs NVIDIA RTX 4090
AMD Radeon RX 7900 XTX vs NVIDIA RTX 4090 for local LLMs
Across 6 tests measured on both, the NVIDIA RTX 4090 is faster in 4 and generates a median 1.68× the tokens/s of the AMD Radeon RX 7900 XTX.
On Qwen3.8 27B (Q4_K_M, llama-server) the AMD Radeon RX 7900 XTX generates 30.7 tokens/s and the NVIDIA RTX 4090 47.7 tokens/s (measured).
Same model, same quant, same test
| Model | Quant / test | Radeon RX 7900 XTX tok/s | RTX 4090 tok/s | Faster | Sources and run details |
|---|---|---|---|---|---|
| Qwen3.8 27B | Q4_K_M llama-server | 30.7 | 47.7 | RTX 4090 +55% | qwen38-mtp Radeon RX 7900 XTX · qwen38-mtp RTX 4090 |
| Qwen3.8 27B | UD-Q4_K_XL llama-server | 41.0 Vulkan | 40.4 CUDA | even | qwen38-mtp Radeon RX 7900 XTX · qwen38-mtp RTX 4090 |
| Llama 2 7B | Q4_0 llama-bench | 191 Vulkan | 190 Vulkan | even | llama.cpp #10879 Radeon RX 7900 XTX · llama.cpp #10879 RTX 4090 |
| Llama 3.1 8B Instruct | Q4_K_M LocalScore | 42.3 llamafile | 105 llamafile | RTX 4090 +149% | LocalScore Radeon RX 7900 XTX · LocalScore RTX 4090 |
| Llama 3.2 1B Instruct | Q4_K_M LocalScore | 78.4 llamafile | 292 llamafile | RTX 4090 +273% | LocalScore Radeon RX 7900 XTX · LocalScore RTX 4090 |
| Qwen2.5 14B Instruct | Q4_K_M LocalScore | 26.8 llamafile | 49.1 llamafile | RTX 4090 +83% | LocalScore Radeon RX 7900 XTX · LocalScore RTX 4090 |
Generation speed in tokens/s, best measured backend for each chip (shown under the number). Backends can differ between the two chips; check them before drawing conclusions. Measured results only, nothing estimated.
Specs
| AMD Radeon RX 7900 XTX | NVIDIA RTX 4090 | |
|---|---|---|
| Memory | 24 GB | 24 GB |
| Memory bandwidth | 960 GB/s | 1008 GB/s |
All results for the AMD Radeon RX 7900 XTX · All results for the NVIDIA RTX 4090 · More comparisons