NVIDIA RTX 5080 vs AMD RX 9060 XT 16GB for local LLMs
23 reports on the NVIDIA RTX 5080 and 5 on the AMD RX 9060 XT 16GB
Which is faster for local LLMs?
On Qwen2.5 14B at 4-bit, the NVIDIA RTX 5080 has 93.4 generation tokens/s (one run); prompt processing 4842.2 tokens/s (one run); the AMD RX 9060 XT 16GB has 33.5 generation tokens/s (one run); prompt processing 1210.3 tokens/s (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 3.0x higher on the NVIDIA RTX 5080 (960 GB/s on the NVIDIA RTX 5080, 320 on the AMD RX 9060 XT 16GB).
- Memory
- 16GB
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 225 TFLOPS
- Reports
- 23
- Memory
- 16GB
- Memory bandwidth
- 320 GB/s
- FP16 compute
- 103 TFLOPS
- Reports
- 5
Measured on both
Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | NVIDIA RTX 5080 | AMD RX 9060 XT 16GB |
|---|---|---|
| Qwen2.5 14B4-bit | 93.4one runPP 4842.2 (one run)Ollama16K context | 33.5one runPP 1210.3 (one run)llama.cppcontext not stated |
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape. Where a model was also measured above, the measurement wins.
| Model | NVIDIA RTX 5080 | AMD RX 9060 XT 16GB |
|---|---|---|
| Qwen2.5 14B | 86.2 t/sQ3_K_M | 28.7 t/sQ3_K_M |
| Qwen3.8 27B | 62.6 t/sQ2_K | 20.9 t/sQ2_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 207.0 t/sQ2_K | 69.0 t/sQ2_K |
| Qwen3.6 27B | 62.6 t/sQ2_K | 20.9 t/sQ2_K |
| Gemma 4 26B · 4B active | 139.6 t/sQ3_K_S | 46.5 t/sQ3_K_S |
Change the context, RAM or model in the calculator: NVIDIA RTX 5080 · AMD RX 9060 XT 16GB
Every report on each card, with its source: NVIDIA RTX 5080 · AMD RX 9060 XT 16GB