NVIDIA RTX 5080 vs AMD RX 6700 XT for local LLMs
27 reports on the NVIDIA RTX 5080 and 4 on the AMD RX 6700 XT
Which is faster for local LLMs?
On Qwen3 8B at 4-bit, the NVIDIA RTX 5080 has 130.6 generation tokens/s (one run); the AMD RX 6700 XT has 61.0 generation tokens/s (one run); prompt processing 851.0 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 2.5x higher on the NVIDIA RTX 5080 (960 GB/s on the NVIDIA RTX 5080, 384 on the AMD RX 6700 XT).
- Memory
- 16GB
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 225 TFLOPS
- Reports
- 27
- Memory
- 12GB
- Memory bandwidth
- 384 GB/s
- FP16 compute
- 26.4 TFLOPS
- Reports
- 4
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 6700 XT |
|---|---|---|
| Qwen3 8B4-bit | 130.6one runllama.cpp40K context | 61.0one runPP 851.0 (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 6700 XT |
|---|---|---|
| Qwen3 8B | 81.2 t/sQ6_K | 60.3 t/sQ3_K_M |
| Qwen3.8 27B | 62.6 t/sQ2_K | 1.6 t/sQ8_0, layers on CPU |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 207.0 t/sQ2_K | 13.3 t/sQ6_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 62.6 t/sQ2_K | 1.6 t/sQ8_0, layers on CPU |
| Gemma 4 26B · 4B active | 139.6 t/sQ3_K_S | 62.7 t/sQ2_K |
Change the context, RAM or model in the calculator: NVIDIA RTX 5080 · AMD RX 6700 XT
Every report on each card, with its source: NVIDIA RTX 5080 · AMD RX 6700 XT