AMD RX 9070 XT 16GB vs NVIDIA V100 16GB for local LLMs
9 reports on the AMD RX 9070 XT 16GB and 10 on the NVIDIA V100 16GB
Which is faster for local LLMs?
On Qwen3.5 9B at 6-bit, the AMD RX 9070 XT 16GB runs at 62.0 tokens per second (one run) and the NVIDIA V100 16GB at 4.6 (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 41% higher on the NVIDIA V100 16GB (640 GB/s on the AMD RX 9070 XT 16GB, 900 on the NVIDIA V100 16GB).
- Memory
- 16GB
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 195 TFLOPS
- Reports
- 9
- Memory
- 16GB
- Memory bandwidth
- 900 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 10
Measured on both
Median tokens per second 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 quant level. Engines and context lengths can still differ between the runs. How to read these
| Model | AMD RX 9070 XT 16GB | NVIDIA V100 16GB |
|---|---|---|
| Qwen3.5 9B6-bit | 62.0one run | 4.6one run |
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 | AMD RX 9070 XT 16GB | NVIDIA V100 16GB |
|---|---|---|
| Qwen3.5 9B | 39.1 t/sQ8_0 | 55.0 t/sQ8_0 |
| Qwen3.8 27B | 41.7 t/sQ2_K | 58.7 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 | 138.0 t/sQ2_K | 194.1 t/sQ2_K |
| Qwen3.6 27B | 41.7 t/sQ2_K | 58.7 t/sQ2_K |
| Gemma 4 26B · 4B active | 93.0 t/sQ3_K_S | 130.8 t/sQ3_K_S |
Change the context, RAM or model in the calculator: AMD RX 9070 XT 16GB · NVIDIA V100 16GB
Every report on each card, with its source: AMD RX 9070 XT 16GB · NVIDIA V100 16GB