AMD RX 6700 XT vs NVIDIA Tesla P100 16GB for local LLMs
5 reports on the AMD RX 6700 XT and 15 on the NVIDIA Tesla P100 16GB
Which is faster for local LLMs?
On Qwen3.8 27B at 3-bit, the AMD RX 6700 XT has 10.0 generation tokens/s (one run); the NVIDIA Tesla P100 16GB has 10.0 generation tokens/s (one run). Memory bandwidth, which caps how fast a card can write, is 1.9x higher on the NVIDIA Tesla P100 16GB (384 GB/s on the AMD RX 6700 XT, 732 on the NVIDIA Tesla P100 16GB).
- Memory
- 12GB
- Memory bandwidth
- 384 GB/s
- FP16 compute
- 26.4 TFLOPS
- Reports
- 5
- Memory
- 16GB
- Memory bandwidth
- 732 GB/s
- FP16 compute
- 19 TFLOPS
- Reports
- 15
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 | AMD RX 6700 XT | NVIDIA Tesla P100 16GB |
|---|---|---|
| Qwen3.8 27B3-bit | 10.0one runengine not statedcontext not stated | 10.0one runengine not statedcontext 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 | AMD RX 6700 XT | NVIDIA Tesla P100 16GB |
|---|---|---|
| Qwen3.8 27B | 1.6 t/sQ8_0, layers on CPU | 47.7 t/sQ2_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 13.3 t/sQ6_K, experts in RAM | 157.9 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 1.6 t/sQ8_0, layers on CPU | 47.7 t/sQ2_K |
| Gemma 4 26B · 4B active | 62.7 t/sQ2_K | 106.4 t/sQ3_K_S |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: AMD RX 6700 XT · NVIDIA Tesla P100 16GB
Every report on each card, with its source: AMD RX 6700 XT · NVIDIA Tesla P100 16GB