NVIDIA RTX 4080 Super vs NVIDIA Tesla P100 16GB for local LLMs
6 reports on the NVIDIA RTX 4080 Super and 13 on the NVIDIA Tesla P100 16GB
Which is faster for local LLMs?
On Qwen3.8 27B at 3-bit, the NVIDIA RTX 4080 Super has 33.1 generation tokens/s (one run); the NVIDIA Tesla P100 16GB has 10.0 generation 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 about the same on both (736 GB/s on the NVIDIA RTX 4080 Super, 732 on the NVIDIA Tesla P100 16GB).
- Memory
- 16GB
- Memory bandwidth
- 736 GB/s
- FP16 compute
- 209 TFLOPS
- Reports
- 6
- Memory
- 16GB
- Memory bandwidth
- 732 GB/s
- FP16 compute
- 19 TFLOPS
- Reports
- 13
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 4080 Super | NVIDIA Tesla P100 16GB |
|---|---|---|
| Qwen3.8 27B3-bit | 33.1one runllama.cpp72K context | 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 | NVIDIA RTX 4080 Super | NVIDIA Tesla P100 16GB |
|---|---|---|
| Qwen3.8 27B | 48.0 t/sQ2_K | 47.7 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 | 158.7 t/sQ2_K | 157.9 t/sQ2_K |
| Qwen3.6 27B | 48.0 t/sQ2_K | 47.7 t/sQ2_K |
| Gemma 4 26B · 4B active | 107.0 t/sQ3_K_S | 106.4 t/sQ3_K_S |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: NVIDIA RTX 4080 Super · NVIDIA Tesla P100 16GB
Every report on each card, with its source: NVIDIA RTX 4080 Super · NVIDIA Tesla P100 16GB